Ca
Calem v0.1
Deerfield Green · Prototype
Multi-agent marketing AI

Deerfield Green · Prototype

Calem

A multi-agent marketing-strategy team on LangGraph. Specialist roles draft a campaign, an evaluator scores it, a repair loop revises the weakest part, a human approves.

7 Role Agents
10 Rubric Dimensions
0.72 Quality Threshold
≤2 Auto-Repair Attempts

Calem is a multi-agent AI marketing-strategy system built on LangGraph. Seven specialist role agents collaborate to draft a full campaign — brand voice, ICP, offers, SEO, content, ads, and competitive intelligence. An LLM evaluator scores the draft against a weighted 10-dimension rubric; a repair loop targets the weakest role and reruns it up to twice. A human approval gate holds before any deliverable ships.

The team

Seven specialist agents, each with a fixed scope and a spliced brand-voice constraint.

brand_voice foundation

Declares one voice archetype once after memory; every downstream role is spliced with this spec so tone never drifts.

icp fan-out

Dynamic Send fan-out: N candidate agents draft personas in parallel, a consolidator writes the canonical ICP profile.

offers commercial

Commercial architecture — motion, pricing tiers, trial/POC structure, alternates, dated urgency, verb-led CTAs.

seo organic

Intent-grouped keyword clusters, competitive gaps, pillar/spoke internal-link patterns matched to the funnel mix.

content editorial

Quarterly theme tied to one ICP pain; calendar of 5–10 pieces with format, cadence, distribution, hero asset.

ads paid

Channel + funnel-stage + attribute-level targeting + creative test matrix (headline × hook × CTA × visual).

competitive_intel tool-using

The only tool-using role — a Tavily ReAct loop; emits research_context telemetry to prove real tool use.

Built on LangGraph 1.x + FastAPI + Pydantic v2. State: Postgres (checkpoints), Dragonfly (org memory), Qdrant (BGE-M3 hybrid grounding). Single model (Kimi K2.6 via Novita).