Findings & Knowledge
Two complementary systems for tracking issues and accumulating context during workflow execution
Overview
When a unified workflow runs its verification-agentic loop, the runner captures two kinds of structured data: findings and knowledge entries. They serve different audiences and have different lifecycles, but work together to make each iteration smarter than the last.
In short: Findings are for you (the user) to track issues. Knowledge is for the AI to learn from past iterations. Both are visible in the Summary page after a workflow completes.
At a Glance
Findings
Structured issue tracker with lifecycle management
- Parsed from AI output markers
- Has status flow: detected, in progress, resolved
- Categorized by type: bug, security, performance
- Severity levels: critical, high, medium, low
- Deduplicated across sessions
- Supports user input requests
Knowledge
Cross-iteration context for smarter retries
- Recorded automatically by the runner
- Categories: verification feedback, observation, solution
- Tracks which iteration created each entry
- Fed back into the AI's prompt on the next iteration
- Resolved automatically when verification passes
- Visible in Summary page's Knowledge tab
Findings
Findings are structured issues detected during workflow execution. They work like a built-in issue tracker — each finding has a category, severity, and lifecycle status.
How findings are created
The AI emits findings using special markers in its output:
[FINDING:code_bug:high]
Title: Null pointer in login handler
Description: The user object is not checked
for null before accessing .email
File: src/auth/login.ts
Line: 42
[/FINDING]Finding categories
Status lifecycle
Findings can also be marked as wont_fix, deferred, or needs_input (waiting for your decision).
Deduplication
Each finding has a signature hash computed from its category, title, and code location. If the AI reports the same finding across multiple iterations or sessions, it won't create duplicates.
Knowledge Entries
Knowledge entries are the runner's memory system. They accumulate context across iterations of the verification-agentic loop so the AI doesn't repeat mistakes or lose track of what it has learned.
How knowledge is recorded
The runner automatically records knowledge at key points during workflow execution. You don't need to do anything to enable it.
After verification fails
Category: verification_feedback
Records which checks failed and why, so the AI knows exactly what to fix on the next attempt
After agentic phase completes
Category: finding, root_cause, solution, observation
Parses the AI's output for [FINDING:type] markers and stores them as knowledge entries for cross-iteration context
When verification passes
Category: (all categories)
All unresolved knowledge entries are automatically marked as resolved since the issues they describe have been addressed
Knowledge categories
verification_feedbackWhat verification checks failed and detailed failure contextfindingA discovered issue in the codebase or configurationroot_causeAn identified root cause of a problemsolutionA fix that was attempted or appliedobservationGeneral context about execution progress or outcomeenvironmentInfrastructure issues (missing tools, disk space, permissions)How knowledge improves the AI
On iteration 2 and beyond, the runner builds a Previous Iteration Context section from accumulated knowledge and injects it into the AI's prompt. This includes:
- 1.The most recent verification feedback (what failed and why)
- 2.Unresolved findings and root causes from earlier iterations
- 3.Previous solution attempts (so the AI doesn't retry failed approaches)
- 4.Recent observations about execution state
How They Work Together
Findings and knowledge are complementary. The same information can exist in both systems, serving different purposes:
Example: A bug is found during iteration 1
The AI identifies a null pointer bug and outputs a [FINDING:code_bug:high] marker
A finding is created in the Findings tab with status "detected" — you can see it, filter it, and track its resolution
A knowledge entry is also created with category 'finding' — this feeds into the AI's context on the next iteration
When verification runs again and fails, the failure details are recorded as verification_feedback knowledge
On iteration 2, the AI receives all of this as context — it knows what it found, what it tried, and what still fails
When verification finally passes, all knowledge entries are marked as resolved
Where to See Them
Findings Tab
Shows all findings for a task run, with filters for category, severity, and status. Available in the task run detail view.
Summary page > Findings tabKnowledge Tab
Shows knowledge entries grouped by iteration, with category labels and resolution status. Appears in the Summary page after workflow completion.
Summary page > Knowledge tabRunner API
Query findings and knowledge programmatically via the runner's HTTP API for integration with external tools.
http://localhost:9876/task-runs/{id}/knowledgeAPI Access
Both findings and knowledge entries can be queried via the runner's HTTP API:
/task-runs/{id}/knowledgeAll knowledge entries for a task run
/task-runs/{id}/knowledge?category=findingOnly findings/bugs from knowledge
/task-runs/{id}/knowledge?unresolved_only=trueOnly unresolved knowledge entries
Detailed Comparison
| Aspect | Findings | Knowledge |
|---|---|---|
| Primary audience | You (the user) | The AI agent |
| Purpose | Issue tracking with lifecycle | Cross-iteration context propagation |
| Created by | Parsed from AI output markers | Recorded automatically by runner |
| Status lifecycle | detected > in_progress > resolved / wont_fix | Unresolved or resolved (binary) |
| Deduplication | Yes (signature hash) | No |
| User interaction | Supports needs_input / user_response | No user interaction |
| Iteration tracking | Session-level only | Explicit iteration field |
| Feeds back to AI | Included in iteration context | Primary source of iteration context |
| Auto-resolved | No | Yes, when verification passes |
| Database table | task_run_findings | task_knowledge |