EthosPowerAISolution · Intelligence
Second Brain — One Week, Three Human Gates
- Telegram
- Whisper
- Ollama
- Neo4j
- Qdrant
- Honcho
- Frappe CRM
- Listmonk
- Windmill
- DeerFlow
- Claude Agent SDK
- Postiz
The problem
Context evaporates faster than anyone can type it. A name from a site visit, a promise made in a corridor, a battery that will be past its end-of-life date by winter, each is lost between the moment it happens and the next time someone sits at a desk. The tools sold for this assume a structured capture session that rarely occurs. The 'autonomous outreach' products fill a prospect's inbox with mail nobody read before it left. I wanted neither, so I built the opposite.
What I built
A sales-intelligence system that takes its orders from one phone, runs on a VPS and a home lab, and sends nothing to a prospect until a human taps a button. At seven each morning a single Telegram message reports what the lead scorer and the equipment monitor did overnight, while a cron outside the workflow engine confirms the engine itself is still alive. Then the day starts, and a thirty-second voice note is transcribed on the home GPU, its names, sites, equipment and standards pulled out by a local model, and the result written three times, to the graph, the vector store and the CRM, each copy pointing at the other two. The follow-up draft arrives on the phone with two buttons and waits up to a day. Silence means skip, and a second, independent lock must read true before any mail leaves, whatever was tapped. Two crawlers hunt for prospects, one over the public web with Anthropic's model and one sandboxed behind a metered proxy, and neither can write to the CRM; their finds wait in a quarantine queue until an Approve in the browser commits them to all three stores at once or rolls the write back. A sequencer wakes every ten minutes, finds leads that changed stage, and picks one of eighteen templates along four axes. On Monday morning the phone offers three episode topics ranked from what prospects have said. One tap later the script is written from sources it can cite, narrated in a cloned voice, animated scene by scene and staged for a Wednesday contact sheet.
The logic flow
Click any node for what it does, what it hands on, and where a person is required.
What it returns
Voice note to graph, vectors and CRM lead in about 65 seconds, measured. Eighteen nurture templates across stage, engagement, language and brand, and none of them sent to a lead before I have approved that lead once. Three deliberate taps a week are the whole human workload, to send an email, admit a prospect and publish an episode. And the honest status, carried from the system's own notes, is that every video stage through staging has run end to end while the public publish fan-out is deployed, gated and not yet run against a public channel.
Why it fits
The case for this system is not that it makes my old process faster. Bolting AI onto the strategy and the workflow a firm already has only commits it harder to both, and a sales assistant writing my emails faster is exactly that. What is changing instead is the knowledge gap that paid for the last twenty years of this work. I knew the standards, the sizing method and the failure modes; the customer did not. And that gap is not reopening.
A prospect's own assistant now arrives with the load, the string and a defensible first cut, and it did that before anyone picked up a phone, which leaves the firm selling either a number the customer already holds or the judgment that sits on top of it. What the assistant cannot produce is what the assets actually did — the discharge test that fell short in the ninth year, the two sites where the ventilation calculation was right and the installation was not. Second Brain is where that record lives: the system writes it three times over, to the graph, the vector store and the CRM, each copy pointing at the other two, so I can answer from it rather than remember it.
The five-year shape of that, and I offer it as an illustration rather than a plan: make your systems reachable by your customers' own AI tools, which means an API their tools can query under the access rules and the audit trail you set, a record of what your assets did that is worth the query, and a price on the answer rather than on the drawing. The smarter their own tools get, the more often those tools come back to me, which is the opposite of what most firms fear. Three taps a week are the whole human workload here, and each one decides a relationship rather than a document. That is the difference between a supplier and the expert their own AI defers to.
See it run
Want one of these?
Every part of it is open source and self-hostable. What I bring is the failure record and the judgement about where your gates should sit.