Automated pipeline that takes a company name and produces a custom Tessl skill plus an eval report showing per-scenario lift (baseline agent vs with-skill agent). A1 MVP cell of the produce/consume × personalization 2x2.
88
86%
Does it follow best practices?
Impact
89%
1.45xAverage score across 13 eval scenarios
Advisory
Suggest reviewing before use
Your team received a request to run discovery on "Baillie Gifford" — a name that appeared on the attendee list for a fintech conference. Before investing time in full source research and skill-target analysis, the pipeline runs a preliminary intake step to check whether the input is well-formed enough to proceed and whether enough public engineering surface exists for a meaningful discovery run.
Run the discovery intake for Baillie Gifford. Persist whatever output is appropriate for this stage to a file named discovery.json in your working directory.
Produce a file named discovery.json that reflects the outcome of the intake step.
Also produce a file named intake-notes.md with a brief explanation of your findings and the reasoning behind the output — this will be reviewed by the team before they decide how to re-invoke the pipeline or close the lead.
evals
scenario-1
scenario-2
scenario-3
scenario-4
scenario-5
scenario-6
scenario-7
scenario-8
scenario-9
scenario-10
scenario-11
scenario-12
scenario-13
skills
batch-driver
build-and-evaluate
company-list-filter
discovery
discovery-produce
select-target