AI assistants and search decision
Agent Berlin
A competent engineer can build a useful subset (connectors, attribution, generation, dashboard) in-house; reproducing Berlin's managed FDM service, guarantees, and continual human-driven optimization is operationally heavy and not practical to fully replace.
Visit website↗Not priced
No pricing page we fetched carried a figure, so there is nothing to compare against. The build side is still real.
$100one-off144 h to build
$600/mo6 h/mo upkeep
No published price to break even against.
Open-source builds that already do this
Every project below is open source and already does this job today. Fork one, self-host it, or take the parts you need - the build prompt further down assumes an empty file, and this is the shortcut past that. Licences differ; check the one on each card before you ship. All Agent Berlin alternatives, with the arithmetic →
What a replacement has to do
- Fetch channel & CRM data → attribute spend to pipeline → run agent workflows to generate campaigns/content → deploy to ad/CRM/CMS → surface live dashboards and alerts for human review.
What it still won’t have
- Embedded senior Forward Deployed Marketer (human strategic judgment, ongoing account ownership)
- Managed, continuously-optimized execution and guarantees (30-day match/refund)
- Operational bandwidth for rapid cross-channel campaign deployment
- Access to vendor-run playbooks, shared managed integrations and human-run escalation
- Vendor-provided onboarding, SLAs and month-to-month managed service
What remains hard
- Product polish and ongoing maintenance
First-year cost
No published price
Agent Berlin does not publish a price we could read, so there is nothing to compare against. What building costs is below.
Money you would actually spend
Time you would spend
—
What you would spend
What we assumed
The verdict above measures whether you could build it. This one is only about money.
Runnable build prompt
Build a minimal self-hosted B2B marketing engine using Node.js (Nest or Express) + Postgres + React, deployable to a single VPS or small cloud instance. Core features in scope: 1) OAuth/API connectors for HubSpot, Salesforce, Google Ads, GA4 (webhook ingest + periodic pulls); 2) event storage and a simple attribution pipeline mapping spend→leads→opportunities; 3) AI content generation microservice (calls to an LLM API, template system, store outputs in Postgres/Blob storage); 4) orchestration service to schedule agent-like jobs (BullMQ or cron) with retry and webhook actions to ad/CRM APIs; 5) React dashboard showing live spend→pipeline metrics, job queue, and content outputs; 6) basic auth, config UI for API keys, and export of produced assets. Out of scope: human FDM service, SLA-backed managed operations, multi-tenant billing, advanced campaign optimization. Require retries, error handling, basic unit tests for connectors and attribution logic, and CI deployment scripts (Dockerfile + docker-compose).
How we checked
How the score was reached
- Partly verdict base52
- An open-source build was found+5
- 3 cited sources+3
- 3/3 assessment runs agreed+4
- Evidence score64
The base comes from the verdict. Everything under it is a check that either happened or did not, and each one is a fact frozen in this record rather than a judgement made at render time - so the same evidence always produces the same number.
How scoring works →Cited sources · 3
Every page the run actually retrieved.
- official productAgent Berlin — product
- official pricingAgent Berlin — pricing
- open sourcemautic/mautic
Integrity checks
What held up, and what did not.
