Multi-Agent Campaign-Strategy Studio
Conciencia Lab
A 7-agent AI pipeline that codifies high-stakes communications discipline: narrative frames, copy patterns, paid-media doctrine, and reputational guardrails. It runs the full production loop with token-level streaming and human-in-the-loop gates at every step.
- Pipeline
- 7 specialized agents
- Streaming
- Token-level SSE
- HITL
- Every gate
- Stack
- LangGraph · FastAPI · Pinecone
Multi-Agent Campaign-Strategy Studio
The problem
High-stakes communications teams (political campaigns, civic communications, public-affairs operators) work under impossible constraints. Tight cycles, multi-platform output across TikTok, Instagram, X, YouTube, and paid, and reputational shrapnel from any misstep. The tooling on the market was built for marketing teams operating at much lower stakes, so most quality calls happen in human heads, late at night, under deadline. The discipline lives orally and erodes the moment a senior leaves.
The mandate: build a multi-agent AI pipeline that codifies the discipline (narrative frames, copy patterns, paid-media doctrine, reputational guardrails) and runs the production loop with a human in the loop at every gate that matters.
The approach
A 7-agent pipeline, each agent shipped with its own charter, principles, rules, anti-patterns, and heuristics, codified in YAML and Pinecone rather than buried in tribal knowledge. LangGraph for the orchestration spine. FastAPI + Server-Sent Events for the live-streaming UI that lets campaign managers watch the agents reason, interrupt them mid-run, and resume.
The pipeline
- Planner. Validates the campaign request across three input shapes (global OTP, single-piece OTP, agenda-OTI), parses dates, retrieves rules from the doctrine library, and produces a strategic content calendar of CPO ("creative production object") pieces. 14-node LangGraph, with a HITL review gate before approval.
- Creative. Selects a narrative frame per piece (Underdog · Metamorphosis · Rebel Sage · Tribe), applies a copy pattern (PAIPS, VFA, Shame Reframe, Open Loop), and generates beat-by-beat scripts, art direction, and per-platform adaptations. AI-slop blacklist, redundancy, and cognitive-load checks at the guardrail gate.
- Assembly. Decomposes creative briefs into engine-specific generation jobs (fal.ai, Minimax) with engine-aware prompt syntax: modular tokens for U-Net engines, fluent prose for diffusion-transformer engines. It also adds imperfection engineering (high-ISO grain, motion blur) so output reads as filmed rather than generated.
- Quality Check. Three-part QA in parallel: visual defect detection (AI artifacts, format compliance), text correctness (spelling, grammar, brand safety), and semiotic coherence across visual and text. Verdicts: PASS / REVISE / REJECT, with automatic loopback to Creative or Assembly.
- Listening. Ingests post-publication signals (comments, mentions, sentiment), drafts community-management replies, and extracts engagement KPIs.
- Dashboard. Aggregates across campaigns and time periods, surfaces the patterns that mattered (which content types performed, which narratives resonated), and generates concrete next-step recommendations.
- Paid Media. Applies organic-to-paid eligibility (>65% completion-rate threshold), 70-20-10 budget distribution, micro-progressive escalation, and fatigue/frequency detection (frequency >4 and CTR down 25% triggers mandatory rotation). It also runs a reputational shield that rejects rage-bait even when it scores high on raw CTR, because some wins aren't worth taking.
Real-time streaming UI
Token-level SSE streaming so campaign managers watch agents reason live. AbortController cancellation, an interrupt/resume protocol so HITL gates pause execution cleanly, and batch execution with semaphores so a single team can run dozens of requests in parallel without losing per-request context.
Doctrine-driven, not vibes-driven
Every agent ships with a structured doctrine (charter, principles, rules, anti-patterns, heuristics) backed by Pinecone RAG, so the orchestrator pulls the right rule into the right node at runtime. New campaigns inherit institutional discipline by default, not by training.
The stack
- Backend: FastAPI · LangGraph · SQLAlchemy 2.0 (async) · PostgreSQL · Alembic
- AI / Retrieval: OpenAI · Pinecone (RAG) · Whisper · Make.com generation webhooks · fal.ai · Minimax
- Frontend: Next.js 16 · React 19 · Refine.dev · Ant Design · TypeScript
- Streaming: SSE token-stream · LangGraph checkpointing · interrupt/resume protocol · semaphore-bound batch execution
The impact
- 7 specialized agents wired into one auditable pipeline. Every CPO is traceable from intake through paid-media spend recommendation.
- Real-time streaming UI. Managers watch agents reason, interrupt, redirect, and resume mid-run.
- HITL gates at every quality-critical step. Reputational risk gets caught before publication, not after.
- Doctrine codified, not improvised. Narrative frames, copy patterns, paid rules, and anti-patterns live in the system, not in heads.
- Engine-aware prompt assembly. Content quality compounds because each generation engine receives the syntax it actually responds to.
The platform turns a campaign cycle from a chaos of late-night decisions into a disciplined, observable production line, without taking the human out of the loop.
“On behalf of all of us, I want to express our deepest and most sincere gratitude for the extraordinary work you have carried out over these past months in the development of Conciencia Lab. What we have built together is not only an important, solid, and high-level technological product. It is something greater: concrete proof that when there is talent, commitment, trust, and a shared way of understanding the work, distance ceases to be distance and becomes a bridge. From Paraguay, although we are geographically very far away, we feel an enormous closeness to you today. A closeness born from shared effort, from conversations, from challenges overcome, from the many hours dedicated, and from the conviction that we were creating something with real meaning. Conciencia Lab does not end here. On the contrary: we feel this project is only the beginning of a working relationship with a strong future ahead. We have built not only a tool, but trust. And on that trust, we know new projects, new ideas, and new challenges will come — challenges we will be able to face together. Thank you for your professional excellence, your dedication, your patience, your applied intelligence, and, above all, for being an essential part of this journey. Please receive a warm greeting from Paraguay. From very far away on the map, but very close in the meaning of having done great work together.”
