1 Customer Marketing AI Agent, Live in Production.

1 live agent automates customer marketing within marketing. It runs on demand. It publishes the inputs it needs, the steps it works through and what it hands back.

  • Live

    Case Study Creation

    Turn a customer interview into a case study — challenge, approach, results and verbatim quotes — with every figure traced back to the transcript and nothing published without approval.

Tracing every figure in the case study back to the transcript

Case studies carry more risk than their length suggests, because the numbers in them are quoted back to you. The interview produces something approximate — a customer says the process used to take “about a week, maybe more” — and the draft says five days, and the published version says the time was cut by sixty percent. Nobody lied at any step; each rounding was reasonable, and the compound result is a figure the customer would not endorse if asked. That matters practically: a prospect cites the case study in a sales conversation, the reference call happens, and the customer does not recognise their own numbers. The other cost is latency — a case study written weeks after the interview is reconstructed from notes, which is when quotes get tidied into things nobody said.

Case Study Creation turns a customer interview into a case study — challenge, approach, results and verbatim quotes — with every figure traced back to the transcript and nothing published without approval. The traceability is the safeguard against compound rounding, and keeping quotes verbatim is what makes a reference call go well rather than badly. One agent covers this process. Approval is required twice in practice: internally, and by the customer, because a case study is a statement made on their behalf and the only person who can authorise that is them.

What this moves

Published figures the customer will stand behind
Each number is traced back to the interview transcript, so nothing appears that the customer did not actually say.
Time from interview to a reviewable draft
Challenge, approach, results and verbatim quotes are structured from the transcript directly, rather than reconstructed from notes weeks later.

Marketing

How AI agents handle customer marketing

Drawn from the 1 agent above — what they require, how they run, and what comes back.

What they need

  • Interview transcript
  • Permissions and framing

What comes back

  • The story Metadata grid
  • Results claimed Table of results
  • Draft case study Markdown doc
  • Traceability checks Verification checklist
  • Before it goes to the customer Validation result

How they run

Run on demand
1
Steps per run
4
Credits per run
8

Where customer marketing fits in marketing

Competitor tracking, market monitoring and content briefs are the slow part of a campaign. Agents keep that running continuously, so a launch is not waiting on someone to go and read things.

All 20 marketing agents

Next Step

Deploying customer marketing agents

These run as-is against the inputs listed above. Most deployments adapt one — a different source system, a different tolerance, a different approval path. The first call establishes which.

Book a Technical Call
  • No sales script
  • NDA on request
  • Scoping notes sent within 48 hours
Call us Book a call