Issues

Issue Index

• Action Changed Something Else Too

  An AI or agent action makes the requested change but also changes another object, field, file, state, rule, or workflow element that was not supposed to change.

  Category: Spread & Escalation | Patterns: 3 | Primary lenses: 4 | Secondary lenses: 2

• Action Triggered by Confidence Score

  A confidence score, certainty label, risk level, or probability-like value triggers an action without enough approval, calibration, or authority control.

  Category: Permissions & Approvals | Patterns: 3 | Primary lenses: 5 | Secondary lenses: 4

• Actual Policy Differs From Declared Policy

  The policy the AI or workflow actually follows differs from the policy that is documented, declared, displayed, or expected.

  Category: Rules & Policies | Patterns: 3 | Primary lenses: 4 | Secondary lenses: 1

• Agent Cannot Choose Tool Without Tool Result

  The agent needs a tool result to choose the right tool, but cannot obtain that result without choosing a tool first.

  Category: Loops & Resolution | Patterns: 3 | Primary lenses: 5 | Secondary lenses: 2

• Agent Gets Conflicting Tool Authority

  An agent receives conflicting authority signals about whether, when, or how it may use a tool, connector, function, or integration.

  Category: Permissions & Approvals | Patterns: 3 | Primary lenses: 3 | Secondary lenses: 3

• Agent Keeps Expanding the Task

  The agent repeatedly expands the task, plan, scope, or next-step list instead of completing the declared work.

  Category: Agents | Patterns: 3 | Primary lenses: 5 | Secondary lenses: 3

• Agent Modified Unrelated State

  An agent changes state outside the requested task, target, file, record, workflow, or authorized scope.

  Category: Scope & Boundaries | Patterns: 3 | Primary lenses: 4 | Secondary lenses: 0

• Agent Never Settles on Final Answer

  The agent keeps revising, rechecking, planning, or branching instead of converging on a final answer or completed result.

  Category: Loops & Resolution | Patterns: 3 | Primary lenses: 5 | Secondary lenses: 3

• Agent Permission Expands Over Steps

  An agent begins with limited permission but gains, assumes, or exercises broader authority as the workflow continues.

  Category: Spread & Escalation | Patterns: 3 | Primary lenses: 6 | Secondary lenses: 3

• AI Adds Work Not Requested

  The AI adds tasks, steps, analysis, checks, changes, or follow-up work that the user did not ask for.

  Category: Agents | Patterns: 3 | Primary lenses: 5 | Secondary lenses: 1

• AI Forgets Earlier Constraints

  A constraint, instruction, preference, or decision that should persist through the task stops affecting later output.

  Category: Memory & Context | Patterns: 3 | Primary lenses: 4 | Secondary lenses: 2

• AI Memory Has No Governance

  Saved or persistent AI memory affects output without clear rules for ownership, scope, review, update, expiry, or removal.

  Category: Memory & Context | Patterns: 3 | Primary lenses: 5 | Secondary lenses: 4

• AI Memory Updated Without Asking

  AI memory, saved context, preference, or durable state is updated without the user clearly asking for or approving that update.

  Category: Memory & Context | Patterns: 3 | Primary lenses: 5 | Secondary lenses: 4

• AI Output Breaks Parser

  The AI output causes a parser, validator, importer, or structured-output consumer to fail.

  Category: Output | Patterns: 3 | Primary lenses: 3 | Secondary lenses: 3

• AI Touches Unrelated Scope

  The AI affects, edits, analyzes, changes, or reasons over material outside the scope of the requested task.

  Category: Scope & Boundaries | Patterns: 3 | Primary lenses: 5 | Secondary lenses: 1

• AI Uses External Information When Forbidden

  The AI uses outside knowledge, sources, tools, memory, or assumptions after the task forbids external information or limits the allowed source set.

  Category: Scope & Boundaries | Patterns: 3 | Primary lenses: 4 | Secondary lenses: 0

• Answer Has No Traceable Source Link

  The answer makes a claim, recommendation, citation, or factual statement without a source link or trace path that allows the user to verify where it came from.

  Category: Output | Patterns: 3 | Primary lenses: 4 | Secondary lenses: 2

• Answer Has Too Many Paths

  The answer presents too many possible paths, interpretations, options, or next steps without enough structure to choose among them.

  Category: Output | Patterns: 3 | Primary lenses: 4 | Secondary lenses: 2

• Approval Depends on Output That Needs Approval

  A required approval depends on an AI output or workflow result that itself cannot be produced or trusted until approval is granted.

  Category: Loops & Resolution | Patterns: 3 | Primary lenses: 4 | Secondary lenses: 3

• Automation Skips Required Approval

  An automated AI or workflow step proceeds past an approval gate that should have been required before action.

  Category: Permissions & Approvals | Patterns: 3 | Primary lenses: 5 | Secondary lenses: 4

• Behavior Does Not Match Declared Role

  The AI or agent behaves outside, below, or differently from the role, authority, responsibility, or permission posture declared for it.

  Category: Permissions & Approvals | Patterns: 3 | Primary lenses: 4 | Secondary lenses: 4

• Cannot Identify Authoritative State

  The user or workflow cannot tell which state, version, review result, decision, source, or output is currently authoritative.

  Category: Loops & Resolution | Patterns: 3 | Primary lenses: 4 | Secondary lenses: 3

• Citation Points to Wrong Source

  A citation, reference, link, or source pointer is present, but it points to the wrong source, wrong passage, wrong document, or unsupported evidence.

  Category: Output | Patterns: 3 | Primary lenses: 3 | Secondary lenses: 3

• Conflicting Instructions From Different Authorities

  Instructions from different sources, roles, policies, prompts, tools, or workflow authorities conflict without a clear rule for which one governs.

  Category: Rules & Policies | Patterns: 3 | Primary lenses: 3 | Secondary lenses: 1

• Context Changes After Restore

  Restoring, reopening, resuming, or reloading a task changes the context that the AI uses to continue the work.

  Category: Memory & Context | Patterns: 3 | Primary lenses: 4 | Secondary lenses: 1

• Context Leaks Between Tasks

  Context, assumptions, constraints, examples, files, or decisions from one task affect another task where they should not apply.

  Category: Memory & Context | Patterns: 3 | Primary lenses: 4 | Secondary lenses: 3

• Declared Owner Cannot Control Outcome

  A person, role, system, or policy is declared responsible for an outcome but does not have the actual authority or control needed to govern it.

  Category: Permissions & Approvals | Patterns: 3 | Primary lenses: 4 | Secondary lenses: 4

• Diagnostic Area Has No Coverage

  A known diagnostic area, failure mode, requirement, or review dimension has no Issue, check, rubric item, or workflow coverage.

  Category: Coverage & Guidance | Patterns: 3 | Primary lenses: 3 | Secondary lenses: 3

• Downstream Steps Magnify Hallucinated Claim

  A hallucinated or unsupported claim from an AI output is reused by later workflow steps until it becomes more influential than the evidence supports.

  Category: Spread & Escalation | Patterns: 3 | Primary lenses: 5 | Secondary lenses: 1

• Duplicate Fields With Same Meaning

  The AI returns multiple fields, labels, sections, or structured elements that carry the same meaning and create ambiguity about which one should be used.

  Category: Duplication & Overload | Patterns: 3 | Primary lenses: 6 | Secondary lenses: 1

• Duplicate Output Sections

  The AI repeats sections, headings, blocks, or output areas in a way that creates redundancy, confusion, or downstream handling problems.

  Category: Duplication & Overload | Patterns: 3 | Primary lenses: 6 | Secondary lenses: 1

• Early Model Output Gets Overweighted Downstream

  An early AI output receives too much authority in later workflow steps, decisions, reviews, or generated artifacts.

  Category: Spread & Escalation | Patterns: 3 | Primary lenses: 4 | Secondary lenses: 3

• Evaluation Rubric Has Coverage Gap

  An evaluation rubric, grading standard, or review checklist leaves part of the required evaluation space uncovered.

  Category: Coverage & Guidance | Patterns: 3 | Primary lenses: 3 | Secondary lenses: 3

• Fallback Authority Is Missing

  The system does not declare who or what has authority when the primary owner, rule, tool, source, or decision path is unavailable or inconclusive.

  Category: Permissions & Approvals | Patterns: 3 | Primary lenses: 5 | Secondary lenses: 3

• File-Bounded Task Uses Outside Content

  The AI is asked to work only from a specific file or document but uses content, assumptions, or sources outside that file.

  Category: Scope & Boundaries | Patterns: 3 | Primary lenses: 5 | Secondary lenses: 1

• Format Rule Too Weak

  The format instruction is too vague, incomplete, or optional to reliably produce output that satisfies the expected structure.

  Category: Coverage & Guidance | Patterns: 3 | Primary lenses: 4 | Secondary lenses: 3

• Hallucinated Fields

  The AI adds fields, keys, attributes, columns, or structured elements that were not declared, requested, or allowed by the expected schema.

  Category: Output | Patterns: 3 | Primary lenses: 6 | Secondary lenses: 3

• Hidden Rule Overrides Visible Instruction

  A hidden, upstream, system, policy, tool, or product rule changes or overrides the visible instruction the user expects the AI to follow.

  Category: Rules & Policies | Patterns: 3 | Primary lenses: 4 | Secondary lenses: 3

• Human Review and Automation Disagree

  A human review result and an automated AI or workflow result disagree without a declared rule for resolving the difference.

  Category: Workflow & Handoffs | Patterns: 3 | Primary lenses: 4 | Secondary lenses: 3

• Invalid JSON Output

  The AI returns malformed JSON or structured output that cannot be parsed.

  Category: Output | Patterns: 3 | Primary lenses: 3 | Secondary lenses: 4

• Local Exception Grows Into Policy

  A local exception, special case, or one-off allowance begins to function like a general policy.

  Category: Spread & Escalation | Patterns: 3 | Primary lenses: 4 | Secondary lenses: 4

• Local Rule Spreads to Broader Cases

  A rule intended for one local case, file, context, user, workflow, or exception begins affecting broader cases.

  Category: Spread & Escalation | Patterns: 3 | Primary lenses: 5 | Secondary lenses: 1

• Merge Step Leaves Unresolved Differences

  A merge, reconciliation, or consolidation step combines outputs or reviews but leaves important differences unresolved.

  Category: Loops & Resolution | Patterns: 3 | Primary lenses: 4 | Secondary lenses: 3

• Missing Fallback for Unavailable Information

  The task does not declare what the AI should do when required information, sources, tools, fields, or evidence are unavailable.

  Category: Coverage & Guidance | Patterns: 3 | Primary lenses: 3 | Secondary lenses: 5

• Missing Required Fields

  The AI returns structured output that omits fields required by the schema, workflow, parser, form, or downstream consumer.

  Category: Output | Patterns: 3 | Primary lenses: 5 | Secondary lenses: 1

• Model and Workflow Disagree on Next Step

  The AI model recommends or selects a next step that conflicts with the workflow state, required handoff, routing rule, or process sequence.

  Category: Workflow & Handoffs | Patterns: 3 | Primary lenses: 3 | Secondary lenses: 4

• Model Output Triggers Unapproved Action

  AI output causes, recommends, or triggers an action that has not passed the required approval, permission, or authority check.

  Category: Permissions & Approvals | Patterns: 3 | Primary lenses: 6 | Secondary lenses: 3

• Multiple Policies Say the Same Thing

  Multiple policies, rules, or guidance documents express the same requirement, creating redundancy and uncertainty about which one governs.

  Category: Duplication & Overload | Patterns: 3 | Primary lenses: 5 | Secondary lenses: 2

• Nested Fields Do Not Match

  The AI returns nested structured fields whose internal shape, hierarchy, parent-child relationship, or contained values do not match the expected structure.

  Category: Output | Patterns: 3 | Primary lenses: 3 | Secondary lenses: 1

• No Owner for Agent Action

  An agent action can affect the system without a declared responsible owner, authority, or accountable decision path.

  Category: Permissions & Approvals | Patterns: 3 | Primary lenses: 5 | Secondary lenses: 4

• Old Output Expectations Survive Migration

  Expectations from a prior model, prompt, schema, tool, or workflow survive a migration and continue shaping review or downstream handling after they should be replaced.

  Category: Changes & Versions | Patterns: 3 | Primary lenses: 5 | Secondary lenses: 2

• One Prompt Carries Too Many Meanings

  A single prompt carries too many meanings, goals, roles, constraints, or implied tasks for the AI to interpret consistently.

  Category: Duplication & Overload | Patterns: 3 | Primary lenses: 4 | Secondary lenses: 2

• Output Breaks After Model Change

  Output that previously worked begins failing after a model, mode, runtime, or product behavior changes.

  Category: Changes & Versions | Patterns: 3 | Primary lenses: 4 | Secondary lenses: 3

• Output Breaks the Next Step

  The AI output looks acceptable by itself but cannot be used by the next tool, workflow step, parser, reviewer, or downstream consumer.

  Category: MCP, Tools & Integrations | Patterns: 3 | Primary lenses: 3 | Secondary lenses: 3

• Output Changed Without Declared Change

  Output shape, content, format, fields, or behavior changes without a declared change to the prompt, schema, model, workflow, or governing rule.

  Category: Changes & Versions | Patterns: 3 | Primary lenses: 5 | Secondary lenses: 2

• Output Exceeds Length Limit

  The AI output exceeds a declared length, token, word, character, section, field, or size limit.

  Category: Output | Patterns: 3 | Primary lenses: 4 | Secondary lenses: 3

• Parallel Reviews Never Agree

  Parallel AI, human, workflow, or tool reviews keep producing different results without resolving into a shared decision state.

  Category: Loops & Resolution | Patterns: 3 | Primary lenses: 4 | Secondary lenses: 4

• Permissions Conflict After Being Combined

  Permissions, approvals, roles, policies, or authority rules that seem valid separately conflict when combined in the same workflow or AI action.

  Category: Permissions & Approvals | Patterns: 3 | Primary lenses: 3 | Secondary lenses: 1

• Policy Area Has No Examples

  A policy, rule, standard, or guidance area has no examples showing how it should apply to real cases.

  Category: Coverage & Guidance | Patterns: 3 | Primary lenses: 4 | Secondary lenses: 2

• Policy Decision Depends on Itself

  A policy decision requires the outcome of the same policy decision before it can be made.

  Category: Loops & Resolution | Patterns: 3 | Primary lenses: 5 | Secondary lenses: 4

• Policy Exception Spreads Too Far

  A narrow policy exception, allowance, or special case spreads beyond its intended scope and begins governing broader cases.

  Category: Spread & Escalation | Patterns: 3 | Primary lenses: 5 | Secondary lenses: 1

• Policy Update Not Reflected in Output

  A policy, rule, standard, or instruction has been updated, but the AI output still follows the older version.

  Category: Rules & Policies | Patterns: 3 | Primary lenses: 3 | Secondary lenses: 1

• Prompt Behavior Changed Without Version Change

  A prompt begins producing different behavior even though no prompt version, model version, workflow version, or declared dependency change is recorded.

  Category: Changes & Versions | Patterns: 3 | Primary lenses: 5 | Secondary lenses: 2

• Prompt Changed but Workflow Did Not

  A prompt changes but the workflow, parser, review step, routing rule, or downstream expectation still assumes the old prompt behavior.

  Category: Changes & Versions | Patterns: 3 | Primary lenses: 4 | Secondary lenses: 3

• Prompt Does Not Say What to Exclude

  The prompt declares what to include but does not declare what should be excluded, allowing unwanted scope, sources, content, or actions into the result.

  Category: Coverage & Guidance | Patterns: 3 | Primary lenses: 3 | Secondary lenses: 4

• Prompt Has Too Many Valid Interpretations

  The prompt allows too many reasonable interpretations, causing the AI to choose among valid paths without enough guidance.

  Category: Coverage & Guidance | Patterns: 3 | Primary lenses: 4 | Secondary lenses: 2

• Prompt Only Works After Retry

  The prompt fails, misroutes, or produces an unusable response on one attempt but works after retry without a meaningful change to the input.

  Category: Inconsistent Behavior | Patterns: 3 | Primary lenses: 4 | Secondary lenses: 2

• Relationship Map Has Missing Links

  A map of related Issues, rules, patterns, cases, fields, tools, or workflow steps is missing links needed to navigate or reason over the structure.

  Category: Coverage & Guidance | Patterns: 3 | Primary lenses: 3 | Secondary lenses: 3

• Repair Step Created New Breakage

  A repair, correction, retry, or fix step addresses one problem but introduces a new failure elsewhere.

  Category: Spread & Escalation | Patterns: 3 | Primary lenses: 4 | Secondary lenses: 1

• Repeated Constraints Create Confusion

  Repeated constraints, instructions, limits, or exclusions make the task harder to interpret instead of clearer.

  Category: Duplication & Overload | Patterns: 3 | Primary lenses: 5 | Secondary lenses: 2

• Results Vary Too Much

  Repeated or comparable runs produce outputs that vary more than the task, workflow, or user can tolerate.

  Category: Inconsistent Behavior | Patterns: 3 | Primary lenses: 4 | Secondary lenses: 2

• Retrieval Exceeds Evidence Limit

  The AI retrieves, uses, cites, or considers more evidence than the task permits or more than the review surface can support.

  Category: Scope & Boundaries | Patterns: 3 | Primary lenses: 6 | Secondary lenses: 1

• Retry Makes the Problem Worse

  A retry, repair attempt, regeneration, or follow-up instruction increases the error, expands the failure, or creates additional breakage instead of narrowing the problem.

  Category: Spread & Escalation | Patterns: 3 | Primary lenses: 5 | Secondary lenses: 1

• Review Escalates Without Stop Condition

  A review process keeps escalating, re-reviewing, or adding scrutiny without a declared condition for stopping.

  Category: Spread & Escalation | Patterns: 3 | Primary lenses: 5 | Secondary lenses: 2

• Review Outcome Changes Unrelated Environment

  A review result, approval, rejection, or classification changes state outside the environment, case, file, or workflow it was meant to govern.

  Category: Workflow & Handoffs | Patterns: 3 | Primary lenses: 4 | Secondary lenses: 2

• Review Queue Becomes Bottleneck

  A review queue, approval path, or validation stage accumulates too much work and begins blocking the workflow.

  Category: Duplication & Overload | Patterns: 3 | Primary lenses: 4 | Secondary lenses: 3

• Review Rubric Missing Required Criteria

  A review rubric, grading rule, evaluation checklist, or classification standard lacks criteria required to make the review reliable.

  Category: Coverage & Guidance | Patterns: 3 | Primary lenses: 3 | Secondary lenses: 3

• Revoked Approval Still Treated as Active

  An approval, permission, exception, or authorization that was revoked continues to affect AI behavior or workflow decisions as if it were still active.

  Category: Permissions & Approvals | Patterns: 3 | Primary lenses: 3 | Secondary lenses: 1

• Risk Score Triggers Wrong Escalation

  A risk score, severity label, confidence value, or threshold result triggers the wrong escalation path.

  Category: Spread & Escalation | Patterns: 3 | Primary lenses: 5 | Secondary lenses: 4

• Risk Signal Escalates Beyond Evidence

  A risk signal, warning, score, or concern escalates farther than the available evidence supports.

  Category: Spread & Escalation | Patterns: 3 | Primary lenses: 5 | Secondary lenses: 4

• Routing Overrides Task Intent

  Routing, mode selection, agent behavior, or workflow classification sends the task down a path that overrides what the user was trying to accomplish.

  Category: Agents | Patterns: 3 | Primary lenses: 5 | Secondary lenses: 2

• Routing Path Cycles Back to Start

  A routing path sends the case back to the starting point or an earlier step without resolving the condition that caused the route.

  Category: Loops & Resolution | Patterns: 3 | Primary lenses: 5 | Secondary lenses: 2

• Rubric Changed but Results Did Not

  A review rubric, scoring rule, evaluation standard, or classification criterion changes, but AI results continue to reflect the old rubric.

  Category: Changes & Versions | Patterns: 3 | Primary lenses: 3 | Secondary lenses: 1

• Same Case Has Conflicting Policies

  The same case appears to be governed by multiple policies, rules, or standards that point to incompatible outcomes.

  Category: Rules & Policies | Patterns: 3 | Primary lenses: 3 | Secondary lenses: 1

• Same Contract Name Has Different Meanings

  The same prompt, schema, field, policy, tool, or workflow contract name is used in different places with different meanings.

  Category: Changes & Versions | Patterns: 3 | Primary lenses: 4 | Secondary lenses: 2

• Same Instructions Allow Different Outputs

  The same instructions are broad or underspecified enough to allow materially different outputs that all appear compliant.

  Category: Inconsistent Behavior | Patterns: 3 | Primary lenses: 4 | Secondary lenses: 2

• Same Rule Declared in Multiple Places

  The same rule, constraint, instruction, or policy appears in multiple places, creating redundancy and possible drift.

  Category: Duplication & Overload | Patterns: 3 | Primary lenses: 6 | Secondary lenses: 2

• Same Workflow Check Happens Twice

  The same review, validation, approval, routing, or safety check occurs more than once in the workflow without a clear reason.

  Category: Duplication & Overload | Patterns: 3 | Primary lenses: 5 | Secondary lenses: 2

• Saved Memory Not Used

  A saved memory, preference, instruction, or durable context item exists but does not affect the AI output when it should.

  Category: Memory & Context | Patterns: 3 | Primary lenses: 3 | Secondary lenses: 2

• Saved Reference No Longer Works

  A saved source, citation, file reference, prompt reference, or workflow pointer previously worked but no longer resolves to the expected object or meaning.

  Category: Changes & Versions | Patterns: 3 | Primary lenses: 4 | Secondary lenses: 2

• Schema Reference Loops Without Base Case

  A schema, field, type, object, or structured reference points through a loop without a base case that allows validation or interpretation to resolve.

  Category: Loops & Resolution | Patterns: 3 | Primary lenses: 5 | Secondary lenses: 2

• Severity Increases Without New Evidence

  The severity, risk, confidence, or escalation level increases even though no new evidence has been added.

  Category: Spread & Escalation | Patterns: 3 | Primary lenses: 5 | Secondary lenses: 4

• Similar Cases Route to Different Outcomes

  Similar inputs, cases, prompts, or workflow states are routed to different outcomes without a declared difference that explains the split.

  Category: Inconsistent Behavior | Patterns: 3 | Primary lenses: 4 | Secondary lenses: 2

• Single Field Carries Too Many Obligations

  One field, label, score, status, or structured value is expected to carry too many meanings, decisions, or workflow obligations.

  Category: Duplication & Overload | Patterns: 3 | Primary lenses: 6 | Secondary lenses: 1

• Single Step Carries Too Many Decisions

  One prompt, workflow step, review stage, or agent action carries too many decisions for the system or user to evaluate cleanly.

  Category: Duplication & Overload | Patterns: 3 | Primary lenses: 6 | Secondary lenses: 3

• Small Change Produces Large Downstream Effects

  A small prompt, schema, policy, output, or workflow change creates unexpectedly large effects in downstream steps.

  Category: Spread & Escalation | Patterns: 3 | Primary lenses: 5 | Secondary lenses: 3

• Small Error Spreads Into Large Failure

  A small AI, output, routing, or workflow error propagates through later steps until it becomes a larger failure.

  Category: Spread & Escalation | Patterns: 3 | Primary lenses: 4 | Secondary lenses: 1

• Small Issue Keeps Escalating

  A small issue, warning, uncertainty, or correction keeps increasing in severity, scope, or workflow impact across later steps.

  Category: Spread & Escalation | Patterns: 3 | Primary lenses: 4 | Secondary lenses: 1

• Stale Context Affects Output

  Old context, prior instructions, outdated references, or earlier task state continue to affect output after they should no longer apply.

  Category: Memory & Context | Patterns: 3 | Primary lenses: 4 | Secondary lenses: 1

• Task Has No Clear Limit

  The task does not declare where the AI should stop, what is out of scope, or what counts as enough work.

  Category: Scope & Boundaries | Patterns: 3 | Primary lenses: 3 | Secondary lenses: 4

• Task Progress Is Lost Midway

  The AI loses track of completed work, prior decisions, current position, or remaining steps before the task is finished.

  Category: Memory & Context | Patterns: 3 | Primary lenses: 3 | Secondary lenses: 4

• Too Many Tool Calls

  The AI or agent makes more tool calls, searches, retrievals, API calls, or integration actions than the task requires or permits.

  Category: MCP, Tools & Integrations | Patterns: 3 | Primary lenses: 6 | Secondary lenses: 1

• Tool Call Contract Mismatch

  The AI or agent calls a tool with names, arguments, types, modes, or shapes that do not match the declared tool interface.

  Category: MCP, Tools & Integrations | Patterns: 3 | Primary lenses: 3 | Secondary lenses: 3

• Tool Can Act Without Responsible Authority

  A tool, connector, function, or integration can perform an action without a declared responsible authority for that action.

  Category: Permissions & Approvals | Patterns: 3 | Primary lenses: 5 | Secondary lenses: 4

• Tool Exists but Required Inputs Are Missing

  A usable tool or integration exists, but the AI or agent does not have the required inputs, permissions, fields, identifiers, or context needed to call it correctly.

  Category: MCP, Tools & Integrations | Patterns: 3 | Primary lenses: 3 | Secondary lenses: 3

• Tool Result Not Integrated Correctly

  The AI receives a tool result but misreads, ignores, overwrites, misplaces, or fails to incorporate it correctly into the final output or workflow state.

  Category: MCP, Tools & Integrations | Patterns: 3 | Primary lenses: 4 | Secondary lenses: 3

• Tool Rules and Prompt Rules Conflict

  Tool, connector, function, or MCP rules conflict with prompt instructions, causing the AI or agent to face incompatible requirements.

  Category: Rules & Policies | Patterns: 3 | Primary lenses: 3 | Secondary lenses: 3

• Validation Result Changes on Retry

  A validation, grading, review, classification, or pass/fail result changes after retry even though the input and declared validation rules did not change.

  Category: Inconsistent Behavior | Patterns: 3 | Primary lenses: 5 | Secondary lenses: 3

• Version Change Breaks Existing Prompt

  A prompt that previously produced usable results stops working after a version change in the model, tool, policy, schema, product surface, or workflow.

  Category: Changes & Versions | Patterns: 3 | Primary lenses: 4 | Secondary lenses: 2

• Workflow Loops Through Review Without Resolution

  A workflow repeatedly sends work through review, repair, or escalation without reaching an approved, rejected, or otherwise resolved state.

  Category: Loops & Resolution | Patterns: 3 | Primary lenses: 5 | Secondary lenses: 2

• Workflow Stage Has Too Few Checks

  A workflow stage lacks enough checks, gates, criteria, or review conditions to safely support the work it controls.

  Category: Workflow & Handoffs | Patterns: 3 | Primary lenses: 3 | Secondary lenses: 2

• Workflow Step Has No Decision Owner

  A workflow step requires a decision, approval, judgment, or routing choice, but no owner is declared for making it.

  Category: Workflow & Handoffs | Patterns: 3 | Primary lenses: 3 | Secondary lenses: 4

• Workflow Step Lacks Required Conditions

  A workflow step can run, route, approve, reject, or continue without the required conditions being declared or checked.

  Category: Workflow & Handoffs | Patterns: 3 | Primary lenses: 2 | Secondary lenses: 4

• Workflow Waits on Step That Waits Back

  A workflow step waits for another step that also waits on the first step, creating a blocking loop.

  Category: Loops & Resolution | Patterns: 3 | Primary lenses: 4 | Secondary lenses: 3

• Wrong Field Types

  The AI returns fields with values whose types do not match the expected schema, such as strings where numbers, booleans, arrays, objects, or enums are required.

  Category: Output | Patterns: 3 | Primary lenses: 3 | Secondary lenses: 3