The agentic pipeline

Seven agents. One studio.

LLM agents run discovery, content iteration, knowledge-graph build, instrumentation, statistical honesty, and pre-ship QA on every engagement. Not as marketing. As production tooling.

Discovery agent

All tiers

Runs the structured client interview. Same rubric as Tyler's week-one discovery, in five minutes.

Status · Live at /agents/intake

Customer acquisition agent

Constellation

Top-of-funnel discovery, prospect qualification, and pipeline state management. Built and shipped through the studio (originally by Tyler), currently licensed to a B2B SaaS partner and running in production. We build similar bespoke agents for client teams at Constellation tier.

Status · Licensed · production

Knowledge-graph agent

Summit+

GraphRAG over the client's research, prior content, and domain corpus. Turns unstructured material into a query surface that survives team turnover.

Status · Per engagement

Content iteration agent

Summit+

Generates variants of long-form deliverables from a brief, surfaces them for human review, learns from selections.

Status · Per engagement

Instrumentation agent

Summit+

Sets up performance dashboards. Wires KPI capture into the deliverable from build week, not launch week.

Status · Per engagement

Statistical-honesty agent

All tiers

Gates every public claim through the measurement policy. Flags directional-tier claims dressed up as validated.

Status · Per engagement

QA agent

All tiers

Pre-ship deliverable review. Visual rubric pass, runtime error scan, voice-rule check before anything leaves the studio.

Status · Per engagement
How we think about it
  • Agents are production tooling. Not marketing. Not features.
  • Agents handle the structured work humans do badly (consistent rubrics, exhaustive checklists, large-corpus retrieval).
  • Humans handle the work agents do badly (taste, judgment calls, conversations with real stakeholders).
  • When an agent can't make the call, it surfaces the decision to a human. It does not guess.
  • Every agent claim that reaches the client carries an evidence tier. Same discipline as the measurement policy.
Try the discovery agent

The intake agent runs the same five-minute discovery the studio uses in week one.

You'll get a one-page brief, a tier recommendation, and an honest no-fit answer if your problem belongs somewhere else.

The agent is an AI. It will not pretend to be Tyler.

Honest note

Two of the seven agents above are visible from the outside: the discovery agent (you can talk to it at /agents/intake) and the customer acquisition agent (already licensed and running in production with a SaaS partner). The other five ship as part of engagement deliverables, not as public chat surfaces.

If you want to see the engagement agents in action, the path is Atlas. By week three of an Atlas engagement, the relevant agents are running on your project.