What it owns
- Known client/account context
- Business links and bounded site reconnaissance
- Stakeholders, systems of record and constraints
- Conversation history and unresolved discovery questions
P01 · Demand knowledge node
Client intelligence and discovery
Begin with everything Actionist already knows, enrich it with bounded public business context, then ask only the questions needed to identify valuable workflows.
Problem boundary
What this subsystem owns and what it must hand to the rest of Actionist.
What research already found
- Actionist can pre-populate client context before chat
- A generic “what app do you want?” prompt wastes known information
- The useful target is a painful workflow and measurable outcome, not a feature wishlist
Open first-principles questions
- Which Actionist client fields are canonical?
- What may be scraped automatically?
- How do we distinguish stated wants from observed workflow pain?
- What confidence threshold triggers a follow-up question?
Inputs
- Actionist account profile
- Client URLs
- Conversation
- Existing tools
Outputs
- ClientContext
- DiscoveryGapList
- CandidateOutcomes
Connected knowledge nodes
Scientific research protocol
Every research owner uses the same evidence funnel. No padding is allowed when a denominator is inapplicable or evidence is unavailable.
Prior evidence auditRead the canonical spine, all domain-linked artifacts, the 17-industry catalogue and existing contradictions before searching again.
Commercial 100 → 10Define a denominator, map approximately 100 companies/products, and produce first-party dossiers for the strongest 10.
GitHub 100 → 10Search and dedupe approximately 100 relevant OSS projects, then deeply inspect the strongest 10 at the capability and architecture level.
Local estate joinInspect AutoSaaS, Great Library, SISOCRM, 21st stores and other domain-specific precedents already on the laptop.
Innovation 100 → 10Generate a wide divergent idea register, score it against the problem and retain the 10 strongest falsifiable innovations.
First-principles synthesisDecompose the irreducible problem, challenge inherited assumptions, reconcile contradictions and state the minimum sufficient design.
Contracts and experimentsReturn the proposed contract, dependency edges, unknowns, falsifiers, experiments, stop rules and decisions.
Independent verificationA separate verifier checks counts, links, source claims, overlap, contradictions and unsupported conclusions before promotion.
Evidence and agent outputs
Existing research remains source evidence. New agent packets are written to one owned workstream directory and linked here after verification.
| Artifact | Location | State |
|---|---|---|
| Industry atom specifications | research/actionmodel-builder-research-2026-08-26/phase-2/outputs/industry-atom-specifications.md | existing |
| Actionist solutions sweep specification | research/actionist-solutions-sweep-spec-2026-08-26.md | existing |
| Public signals Wave 11 | research/actionmodel-builder-research-2026-08-26/expansion/wave-11/outputs/public-signals-wave-11.md | existing |
| Future verified agent packet | research/workstreams/P01-client-intelligence-and-discovery/runs/<run-id>/ | planned |