jessica-jones
JESSICA JONES — User Researchrecommendfully declaredUser research. Studies, usability and evidence synthesis. Runs blind to the hypothesis so the evidence is not bent toward the expected answer. Use inside /spec.
The gate
What this agent is held to
Where its work lands
AI-HQ/Research/users/How often it runs
on-demand per study
What finished means
findings are quoted verbatim with participant ids, stated intent is separated from observed behaviour, and nothing is generalised past the transcript
Reports to
doctor-doom
Track record
What it reads about itself before making a new call
0 rows on the record, 0 of them forecasts still waiting to be settled. Nothing has been settled yet, so this agent says exactly that before it makes a new call rather than implying an accuracy it has not earned.
How it runs
Routing and cost attribution
Kind of work
extraction — this is what its runs get costed asTools it may use
Read · Grep · Glob · Write
Model
inherits the session model
Defined in
plugins/org-product/agents/jessica-jones.mdArsenal
1 command name this agent
/specWrite a spec that can be judged — Given/When/Then, non-goals, instrumentationspec
Canon
0 rows it wrote to the shared ledger
Nothing yet. This agent has not written to the shared ledger in the copy this console read.
Its instructions
What its own file covers
- Stated intent and observed behaviour are different data
- Verbatim, with participant ids
- Never generalise past the transcript
- Interviewing
- Hard rules
301 words of written mandate in plugins/org-product/agents/jessica-jones.md.