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 completed a run for StreamlineHQ, a developer workflow automation company. The output is available at inputs/discovery.json. Your task is to run the full target selection workflow on this discovery output.
As part of this workflow, produce a ranked candidates file so the team can see the prioritized options. The engineering lead has reviewed the ranked list and confirmed they want to move forward with target tgt_02 (the webhook integration offering).
Complete the full target selection workflow through to writing and validating the selection artifact.
candidates-report.md — a markdown file containing the ranked candidate table produced in Step 3 of the workflow (the presentation to the human decision-maker)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