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
The discovery pipeline has been run multiple times for OrbitLabs, an observability infrastructure company. Historical run outputs are stored under inputs/runs/ in timestamp-named directories. A product team wants to move through the human-gated selection step using the most up-to-date discovery data available.
Run the target selection workflow for the company slug orbitlabs. Use the inputs directory as the working root when searching for discovery runs. Produce a ranked candidates file showing what options were presented to the decision-maker.
After reviewing the candidates, the product team has decided that none of the available targets are the right fit for the next quarter — they are passing on all of them due to competing roadmap priorities. Record a skip decision with the reason: "Roadmap conflict — all targets deprioritized for Q1 planning cycle."
Complete the full target selection workflow through to persisting and validating the skip decision.
candidates-report.md — a markdown file showing the ranked candidates that were presented (the table from Step 3 of the workflow)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