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
A sales team attending an industry summit collected "Alphabet" as a lead to run through the discovery pipeline. Before the pipeline spends time crawling docs and building skill targets, the team wants to know whether the input is ready to process as-is or needs refinement.
Run produce-mode discovery for the company name "Alphabet" and produce the discovery JSON. If the input is ready to process, proceed through the full discovery workflow. If something about the input needs to be resolved before a meaningful discovery can be produced, output the appropriate response so the caller knows what to do next.
Write a file named discovery.json containing the produce-mode discovery result. The JSON should reflect whatever stage of the workflow is appropriate given what you find about "Alphabet" as a company input.
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