[ Start ]
A name or a topic
Farming starts with a customer name, single or as a bulk import from the existing customer base. Hunting starts with topic, description, and region. No more input is needed; the agents do the rest.
[ deep research × sales ]
Deep research for sales: farming and hunting.
Colleagues in sales know the problem: generic outreach reaches nobody, good preparation costs hours per company, and the knowledge about customers and markets lies scattered across the web. That is exactly what this tool grew out of: deep-research agents take over the preparation. In farming, an existing customer is examined until prioritized AI use cases are on the table. In hunting, a search profile becomes a verified list of fitting target companies.
Agent chain
The biggest lever: the agents work together. Every research result becomes the input for the next research task.
Farming
The outcome: researched challenges per customer, mapped to fitting AI solution approaches, prioritized and sourced.
Hunting
The outcome: a list of companies matching the search criteria, verified and with a source per verdict.
Costs under control
Deep-research models are expensive to run. That makes clean architecture non-negotiable: budgets, quotas, no double billing.
[ preparation beats cold calling ]
The best pitch starts long before the conversation.
Selling AI services rarely fails on the offering; it fails on the opening: generic pitches reach nobody, and individual preparation costs hours per company. Deep research makes that preparation scalable: agents with live access to the web do the research that used to be manual work and deliver sourced talking points instead of guesses.
The agents are no black box. Each agent is an editable research brief: the team can rephrase it, reorder it, or add its own, without code. And they work as a chain rather than one-shot: every agent receives its predecessors' results as context, and the order determines what later agents build on.
The result: conversations are held on substance, not on guesses. The point is to solve problems the customer actually feels, instead of placing solutions for problems they do not have. That way every conversation adds value from the first minute: not a sales show, but a discussion about solving problems.
[ two modes, one engine ]
From a name to an analysis, from a topic to a list
Farming means: an existing customer is examined, from the name to prioritized AI use cases. Hunting means: a market is searched, from the search profile to a verified target list. Both modes share the same research engine and differ only in input and output. Every run goes through these stages.
[ Research ]
Agents with live access
Deep-research agents search the open web: annual reports, press, job postings, industry directories, trade-fair lists. Progress is visible live, to the minute, per agent.
[ Build ]
The chain, not one shot
In farming, three agents interlock: profile and process landscape, then challenges, then prioritized AI use cases with a competitor benchmark. Each receives its predecessors' results, and the order is set by drag and drop.
[ Condense ]
From text to tools
From the analysis reports, one click produces a slide deck per use case, a personal email draft, and a newsletter as an Outlook file. Plus a chat assistant that stays strictly inside the research and names its gaps honestly.
[ Validate ]
Hunting with a citation rule
First the breadth search in several passes, until nothing new appears. Then deep validation in small batches: confirmed, unconfirmed, or rejected, every verdict with a source. Nothing is deleted; even rejections stay traceable.
[ Hand over ]
Into daily sales work
The target list goes to sales as an Excel file, CRM contacts are connected, and the analysis reports provide the basis for the conversation. Research becomes a well-prepared first meeting.
[ architecture ]
Research briefs that build on each other
Research engine
Deep research with live web search, no crawler of its own
The research is done by a hosted deep-research model with native web search: the system phrases the brief, the model searches the web and returns a report plus sources. No crawler, no scraping, no search-engine plumbing.
Underneath runs a non-blocking state machine: a waiting agent occupies no compute slot, and the state lives in the database. Stranded runs can be resumed without paying again for agents that already succeeded.
Partial results count too: if a run hits the output limit, a tolerant parser salvages the complete rows. Half a market scan is worth more than none.
Agents & knowledge
Editable research briefs, chained per project
Agents are editable briefs, not code: three per farming project, two per hunt. The team rephrases them, reorders them by drag and drop, and adds its own.
Results are usable three ways: as a report with sources, as searchable full text across all customers, and as a vector for similarity search. Topic clusters across the whole customer base emerge automatically on top.
In hunting, a multi-stage dedupe protects the list: the website domain beats the name, legal forms are normalized, filled fields never overwritten by empty ones.
Sales layer
Reports, slides, drafts, lists, cockpit
Research becomes tools: a slide deck per use case, an email draft, a newsletter as an Outlook file. The chat assistant stays strictly inside the research and says honestly when something is missing.
The target list shows its verification states openly: confirmed, unconfirmed, rejected, with reason and source per row, exportable as an Excel file. CRM contacts are matched.
And costs remain part of the layer: quotas are checked before a run starts, interactive research overtakes bulk imports, and every run is billed individually.
[ lessons ]
Research that costs money needs operational discipline.
The formative incident: the model provider's credit ran out, runs failed, and started research could not be resumed, only deleted and paid for again. That became the foundation of the architecture: durable job state in the database, resumption exactly where a run stopped, and no double billing, even if a process crashes mid-run.
Hunting was just as instructive: in the first version, every agent result replaced the entire list, and whatever the last agent failed to repeat was lost. Today results are merged instead of replaced, truncated output is repaired instead of discarded, and the search runs in passes until a market is truly exhausted. When research costs money, losing none of it is not a nicety; it is the baseline.
[ numbers ]
The system in numbers
3 + 2
deep-research agents in the default chain: three for farming, two for hunting, freely editable and extensible at will
50+
companies from a typical market scan in hunting, searched in passes until nothing new appears
5
tools per customer from one research run: analysis report, slide deck, email draft, newsletter, and chat assistant
to the cent
every research run is accounted for: quotas per user, checked before the start, no double billing
[ technology ]
Technology in use
OpenAI
FastAPI
Celery
Redis
PostgreSQL
OpenAI
FastAPI
Celery
Redis
PostgreSQL
Elasticsearch
React
TypeScript
Docker
Azure
Elasticsearch
React
TypeScript
Docker
Azure
Put the potential of this technology to work.
Wondering how deep research could support your market development or sales? Then let's talk: you bring the challenge, I bring the experience and the tools.