One company · several products · one shared operating system
A plain-language account of Bonaventure: the idea behind it, the four arms, every product with what it does today and what it will do, how a one-person company ships with AI agents, the roadmap, the money, the rules we will not break and the questions we have not answered yet.
Contents
Most company pages tell you what the company wants you to think. This one tells you what the company is. Bonaventure is early: it is being incorporated, it has no revenue yet, and it is built by one founder working with a crew of AI agents. We would rather you learn that from us, in detail, than guess it from a polished landing page.
The document is for three kinds of reader. A potential customer or pilot partner who wants to know what is real before a demo. A potential collaborator or investor who wants to see the whole system and the logic that holds it together. And anyone curious about what an AI-native company looks like from the inside in 2026, including the parts that are still rough.
Everything here comes from the internal documents we actually run the company on: the structure document, the decision log, the monthly plan and the task files. When those change, this document is regenerated. The version and date are on the cover.
Bonaventure builds small, focused businesses on top of one shared operating system.
Some are software products, some are services, and some create content that feeds the products. They do not each get a separate back office. The shared layer is Bonaventure Core: it handles the capabilities that would otherwise be rebuilt again and again, meaning automation, agents, source reading, identity, delivery, measurement and internal control. Product data stays separated; the operating rules are shared. A new product inherits Core's contracts, automation, identity and monitoring rather than rebuilding them.
Mission. Give businesses the system that runs their own growth, and give people transparent access to trustworthy information.
The commercial thesis. AI agents can now perform a large amount of bounded implementation and operations work in parallel, while a human keeps control of accounts, releases, money, legal decisions and customer-facing actions. We are not claiming that one founder and a crew of agents can replace every specialist team. Our claim is narrower: a carefully scoped product can now be built, tested and operated with a cost structure that makes smaller markets commercially viable. The Turkish marketplace seller, the regional B2B sales team, the football fan who wants an honest valuation: these are markets a venture-funded team would not touch. We can.
Why several connected bets, not several unrelated apps. Services create the first cash and the first customer relationships. B2B products turn repeated service problems into software. Undertow is the consumer surface and the local signal layer. The entertainment studios create reusable content for that surface. Core is the infrastructure that keeps those businesses from becoming separate organisations. The point of this document is not to make the portfolio look bigger than it is; it is to show exactly how the pieces are meant to become one company.
What is real on 31 October 2026, in one table. Everything below is expanded in sections 06 to 09.
| Product | Status | What is real today | What is next |
|---|---|---|---|
| Undertow | BETA | iOS app complete; news engine live on one server with about 50 sources; store assets and review notes ready | App Store Connect registration (founder), TestFlight with five testers, review |
| Reach Lead | LIVE | Scanning engine with 242 source recipes, panel in TR/EN, per-customer server, published prices | November gate: five demos, three "I would pay" |
| Reach Call · Qlead | BLOCKED | Designed; waitlist only | Legal opinion on AI calling in Turkey |
| Siftah | BUILT / NOT LIVE | Panel, three marketplace clients, profit report, dry-run flow, login; 180+ tests; no real seller account yet | Pilot seller in December, first subscription in January |
| Bonaventure One · Keelson | BUILT / NOT LIVE | 53 workflows, enterprise sign-in, approval gates, 3,500+ automated checks; zero customer accounts | Provider accounts after incorporation |
| Scoutline | BUILT / NOT LIVE | Factor model, calibration, weekly run, API, accuracy report, static site; all on synthetic data | Licensed data, legal answers, closed test with 20 people |
| Spindrift | BUILT / NOT LIVE | Shared runtime, seven packaged games, store assets | Two App Store games to TestFlight |
| Bergovich | BUILT / NOT LIVE | Album produced; used inside games | Streaming release after legal review |
| Ops · Live | PLANNED | Offer defined; no published rate yet | Rate and services section on the site in November |
| Çırak | IDEA | Concept only | Not scheduled |
Bonaventure is a ship's name ("good fortune, good voyage"), and the products carry names from the same maritime family. The structure is one ship with four arms and a keel.
| Arm | The question it answers | What it contains |
|---|---|---|
| Products | What do we sell the customer? | Software and customer-acquisition tools that let a business manage its own growth; consumer-facing apps. |
| Services | Who does the work when software is not enough? | Bespoke AI solutions and operations powered by Core, plus growth consulting. Quote-based, and the first source of cash. |
| Entertainment | What content do the products get? | Games, scenes, music and football data. Each studio feeds Undertow and, through Core, the other products. |
| Core | What runs all of it? | Eight shared capabilities. Product data stays separate; company identity and the engines are shared. |
Products are ports. The lines between them are currents, and there are three kinds: customers and cash, leads and signals, content and data. This is the map that decides whether an idea is allowed on board.
| From | To | What flows | Kind |
|---|---|---|---|
| Ops / Live | Siftah, One | The first customers, who arrive through consulting and move onto a product | customers & cash |
| Ops and first subscriptions | Core | The first cash pays for the engine | customers & cash |
| Çırak | Siftah | A coached seller becomes a Siftah customer | customers |
| Reach Lead | One, Keelson | Companies showing growth signals become leads inside the growth panel | leads & signals |
| Reach Call + Qlead | Ops | A qualified conversation becomes a consulting engagement | leads & signals |
| Undertow | One, Keelson | Aggregate reaction data by region × generation, with district breakdown; never personal (minimum 50 people per cell) | content & data |
| Spindrift, Bergovich | Undertow | Games, scenes and music as cards in the daily feed | content |
| Scoutline | Undertow | Weekly football value cards, through a contract defined in Core, not a product-specific copy | content |
| Core | every arm | Engines, agents, identity and data | core |
For each product: what it is, what it does today, what is planned, what content or data it produces, and the pricing hypothesis where there is one. Status labels mean exactly what they say.
LIVE running with real users or real data BETA running, closed group BUILT / NOT LIVE working product, no live customer or user yet PLANNED decided and scheduled IDEA not committed BLOCKED built or planned, waiting on a legal or provider dependency
B2C · news and trend cards · the strategic flagship
Undertow is a local-first daily briefing you can play, not scroll forever. A user chooses a district and receives a finite edition of twenty cards that mixes the most relevant local, city, national and world stories with polls, rankings, short games and interactive explainers. The goal is not to keep people in an endless feed; it is to help them understand what matters around them in a few minutes and then leave. It is not a social network: no user content, no profiles, no comments.
B2B · customer acquisition · the first product with a price list
Reach helps small B2B sales teams decide who is worth calling this week. It monitors public business signals, for example a new licence, a tender, a fair participation, a hiring burst or an expansion notice, and turns them into a ranked company list with the source and a plain-language "why now" note. Reach does not replace the CRM; it supplies the CRM with better-timed prospects. The flow is discover (Lead) → call (Call) → qualify (Qlead).
B2B · marketplace seller management · separate product, separate repository
Siftah is an approval-first operating assistant for small Trendyol sellers. ("Siftah" is shop talk for the first sale of the day.) It watches the decisions that are easy to miss during the day, meaning price position, buy-box status and campaign economics, and turns them into concrete actions for the seller to approve. The seller sets the commercial boundaries; Siftah does not cross them on its own.
B2B · growth platform · One for SMBs and digital brands, Keelson for corporates
Bonaventure One is a growth operations panel for businesses that already have customers, campaigns and digital channels but do not have a full CRM or growth team. It brings customer lists and conversion events into one place, builds audience rules, sends approved message journeys through connected channels and measures whether those journeys created results compared with a holdout group that received nothing.
Keelson is the enterprise operating model of One. It is for organisations where the team requesting a campaign, the team approving it and the team executing it are not the same: business units request work, approval rules decide what may proceed, and every unit gets a controlled AI growth workspace without bypassing central governance.
B2C · a coach for people who want to start selling on a marketplace
Çırak ("apprentice") is an early concept for a guided marketplace-startup coach. The intended user is someone who has a product but has never opened or operated a marketplace store. The product would turn that journey into a sequence of decisions, meaning store set-up, listing readiness, pricing, first campaign and first sale, and hand suitable graduates into Siftah. The format (guided tool, course or assistant) and the business model are not decided, and nothing is scheduled.
Entertainment is a studio arm. It does not sell directly; it makes the content that keeps Undertow alive every day and, through Core, gives the B2B products something to say.
Football market values, computed from scratch and explained
Scoutline is an explainable football valuation system. Instead of publishing one unexplained market-value number, it publishes a range and shows the factors that moved a player up or down: age, role, performance, league, contract, club context, marketability and risk. It is a valuation model, not a prediction of the exact fee a future transfer will produce. The public page shows the logic in football terms; a separate methodology page carries the technical detail.
Game studio · AI-native, small, daily
Spindrift is Bonaventure's small-game studio and the game layer behind Undertow. (The name is the spray the wind tears from a wave crest, the surface twin of the undertow.) It uses a limited set of short-session game templates (tap-and-time, swipe-and-choose, sort, guess, rhythm) to turn timely topics into lightweight games that ship without rebuilding the main app. The same templates also become standalone App Store experiments. We do not compete with hyper-casual studios and their user-acquisition budgets.
Music studio
Bergovich is the music studio that supplies original music to the rest of the Bonaventure ecosystem. Its first catalogue, a 20-plus track album produced with a generative music service under a commercial licence, is made for Spindrift games and Undertow's rhythm and discovery experiences, with streaming distribution as a secondary channel. Internal production continues; public commercial release and any rights claims remain gated by legal review of AI-generated music, whose copyright status is unsettled. No revenue is expected from Bergovich on its own.
Services are where the first money comes from, and where the first product customers come from. There is no separate services website; the main site carries the offer.
Bonaventure Ops is the hands-on services arm for companies that need the outcome before they need the software. Three shapes of engagement: Build (we automate a defined process or build a bespoke agent or reporting engine), Operate (we run a growth or operations function for you for a period), Grow (consulting plus execution on a CRM or growth problem). The constraint is that reusable work is built on Core rather than left behind as a one-off script. An Ops customer is the natural first user of Siftah or One.
Bonaventure Live is on-demand expert time for problems that do not need a project. A customer brings a specific CRM, growth, automation or AI-operations question, uses only the minutes needed to work through it, and leaves with a decision or a next-step plan. Larger implementation work moves to Ops rather than staying on a live call. Minutes are bought as credits; the rate and the accepted topics are being set and will be published rather than quoted case by case (the Turkish market range for SMB digital-marketing consulting is roughly 1,500–4,000 TL per hour).
Bonaventure Core is the shared operating layer behind every product. Customers do not buy Core directly. Its job is to stop each new product from rebuilding the same basics (identity, automation, source reading, delivery, agents, monitoring and measurement) and to put the same approval, cost and safety rules underneath all of them. That is what lets a small company launch several products without creating a separate operations team for each one. It is not one program; it is eight capabilities that today live in different repositories and are being pulled together one at a time. Product data stays in its own store; what is shared is identity, the engines and the agents.
| Compartment | What it is | Why it matters to a customer | Where it runs today |
|---|---|---|---|
| Automation engine | A workflow engine on its own server; one flow folder per product; shared error, log and budget counters. Flows write to a queue, so if the engine falls, products keep running from their last state. | A product's automation does not stop when one piece fails, and every product's costs are counted the same way. | n8n in the One/Keelson platform; 53 flows |
| Agent crew | Six lines, nineteen runtime roles: crawler, deduplicator, source warden; writer, variant maker, question master; verifier, compliance, sensitivity; voice agent, qualifier, call analyst; reporter, measurer, insight patterner; and the wardens for budget, anomaly, complaints and ad ceilings. The cheapest model that is good enough, rules without a model where possible. | The same checks (no copied text, no invented numbers, no budget overrun) protect every product, not just the one where they were first built. | Crawling, writing, auditing and the wardens live in the news engine; voice closed pending legal review; analysis in code |
| Crawling engine | Scheduled source reading with robots.txt compliance, one request per source per run, source health scoring, dead-and-stale detection, clustering of the same event. | Reach, Undertow and Scoutline read sources with one engine; a fix for one is a fix for all. | News engine (about 50 sources, every 30 minutes) and Reach Lead (242 recipes); Scoutline reuses it |
| Voice engine | Ninety-second AI calls with an approved script, a qualification rule and a summary from the recording. | When legal review allows it, Reach Call and Ops get calling without a new build. | Closed until the legal opinion arrives |
| Delivery | Sending e-mail, SMS and push with consent-registry checks and per-channel ceilings. | Consent and sending limits are enforced in one place, not re-implemented per product. | In code in One/Keelson; provider accounts come with incorporation |
| Identity | One sign-in contract for every panel: password hashing, signed session tokens, a common cookie, rate limiting, a shared role dictionary, and conformance vectors both implementations must pass. Single sign-on comes after the first paying customer. | A security rule fixed in one panel is fixed in all of them; a customer will eventually sign in once for every Bonaventure product. | Node package live in One/Keelson; Python package live in Reach and Siftah; Undertow stays on its own auth provider with a bridge later |
| Data and Insights | Aggregate, never personal: region × generation × district × card type with at least 50 people per cell. Explainable scoring (the Scoutline factor chain is the pattern) for every product that scores anything. | Insight without profiling: businesses get a picture of a region, never of a person. | Partly in code; the Scoutline score pattern is the reference implementation |
| Bridge | Internal control: the dashboard that shows what every product and agent is doing, what it cost, what is open, and what the human needs to decide. | Everything that needs a human approval shows up in one place. | Live for the news engine (13 tabs) and company-wide internally |
Bonaventure has one founder. The founder owns product decisions, architecture boundaries, accounts and releases; implementation is executed by a crew of AI coding agents, each with a role, and coordinated by a senior model that acts as architect, reviewer and keeper of the decision log. Agents can create implementation work in parallel, but they do not own release authority: every task has a bounded file scope and acceptance criteria, every change is reviewed against that scope, and accounts, secrets, budgets, legal decisions and merges remain human-controlled.
| Who | Role | Rule |
|---|---|---|
| Coordinator (Claude) | Writes the briefs and task files, reviews every pull request, maintains the structure document, the decision log and the plan, keeps the architecture consistent across repositories and stops duplicate work. | Writes no product code beyond one-line fixes. Everything goes through GitHub. |
| Builder agents (three different vendors) | Application screens, Python engines, websites, backend and database, deployment, games and visuals. Each agent has its own clone of each repository. | One open task per agent, one open pull request per product. A fabricated test result means the pull request is rejected. |
| Founder | Merges pull requests, makes decisions, holds every account and every secret, talks to customers. | About thirty minutes a day plus two decision blocks a week. Every decision gets a number in the log. |
The loop. A need is placed in the structure (which arm, which current). The coordinator writes a task file with a file boundary, acceptance criteria and an effort estimate in senior-developer hours. An agent takes a branch, does the work, opens a pull request with the four mandatory sections and the number of tokens it used. The coordinator verifies locally (runs the tests, checks the diff against the boundary, scans for real names and secrets) and comments. The founder merges. The structure document and the plan are updated in the same commit as the decision that changed them; otherwise the decision is not considered closed.
Build evidence. Across the ten repositories, since the first commit in late October 2026: about 170 merged pull requests, roughly 1,100 senior-developer-hours of equivalent work (see the method note in section 11), and 94 test suites with more than 3,500 checks on the largest platform alone. Agent tasks run asynchronously, including overnight; the founder reviews and merges the completed work in the next review block, and nothing reaches a product without that review.
We track three numbers for every task: the effort it would take a senior developer (set by the coordinator from the size and nature of the change), the tokens the agent actually used (reported in the pull request, estimated by a rule if not), and the cost of those tokens at the vendor's list price. From that we get a cost per hour of equivalent work for each agent, and what the whole body of work would have cost if it had all been done by the most expensive agent.
| Measure (31 October 2026) | Value | Note |
|---|---|---|
| Equivalent effort shipped | about 1,100 senior-developer hours | Sum of effort estimates on merged work; the estimate rule is being calibrated as real token counts accumulate |
| Token cost at list price | about 10,000 $ | Most of it is the coordinator's review and design work; the actual bill is lower because of subscription plans and cached context |
| Cheapest builder | about 0.01 $ per equivalent hour | A low-cost model that does most of the volume work under tight briefs |
| Most expensive | about 41 $ per equivalent hour | The coordinator; worth it for review and architecture, wasteful for volume |
| Saved versus doing everything at the top rate | about 36,000 $ | And versus a human team the gap is an order of magnitude larger; we do not publish that number because we cannot measure it honestly |
The point is not that the work is cheap. The point is that the cost curve is flat enough that products for small markets, run by agents with a human on approval, can be profitable at prices those markets can pay. That is the bet.
Running costs today are deliberately small: the news engine on one small cloud machine (a few dollars a month plus a capped AI budget of about one dollar a day), static sites on a free tier, a sports data licence at 19 $ a month, domain names, and the AI subscriptions. Every proposal that adds a monthly cost has to state it.
| # | Line | Time to first payment | Depends on | Unit revenue |
|---|---|---|---|---|
| 1 | Bonaventure Ops / Live | 1–2 weeks after the services section and the rate are published | Founder's hours; an invoicing entity | Hourly rate, to be published |
| 2 | Reach Lead | 4–6 weeks: demos in November, decision gate at month end (5 demos, 3 "I'd pay"), first invoice in December | Ten decision-makers in the target vertical; the euro-invoicing question | From 299 € / month |
| 3 | Siftah | 8–12 weeks: pilot seller in December, first subscription in January | A pilot seller with a real Trendyol account | Subscription, hypothesis 4,900–14,900 TL / month |
| — | Undertow | Not in the revenue order | Strategic visibility, not cash. It stays at the top of the company's priorities for that reason. | |
| — | One / Keelson | After incorporation | Corporate sales are slow; provider accounts need a legal entity. | |
Undertow Plus in month three after launch. Core identity as a single sign-on service after the first paying customer. Reach multi-tenant hosting at ten customers. Siftah consignment after three satisfied sellers. Android for Undertow. Reach Call and Qlead if and when the legal opinion allows. Çırak if Siftah proves the path.
We keep a decision log with 41 numbered decisions so far, and a list of what is still open. The open items that matter most, stated plainly:
| Question | Why it matters | Status |
|---|---|---|
| Incorporation and partnership | The company is not yet a legal entity; a verbal partnership understanding exists and is flagged internally as a risk to be put in writing. | With the lawyer; decision on timing and place pending |
| Founder's existing employment | Side-activity and intellectual-property terms have to be confirmed in writing before certain lines (and the founder's name) appear publicly. | With the lawyer; this is why no founder name appears here |
| News publishing rights | Many Turkish news sources forbid reproduction. Our model is headline + own summary + link, but public launch of the news feed waits for an opinion. | Gate before public launch; sources approved one by one |
| AI voice calling | Reach Call and Qlead are closed until the legal position on automated calls is clear. | Waitlist only |
| Scoutline and personality rights | Publishing a value under a real player's name, correction and removal, the data licence's derivative-work and mass-media clauses, distance from betting. | Eight questions filed; synthetic data until answered |
| Euro pricing for a Turkish company | Showing euro prices and invoicing in lira may conflict with currency rules. | With the lawyer; euro prices stand meanwhile |
| AI-generated music | Copyright protection for generated works is unsettled. | Asked; not blocking |
| Does anyone pay? | Reach's November gate (5 demos, 3 "I'd pay") is the first real test of the whole thesis. | Open until 30 November 2026 |
Risks we watch and the early signal for each: a data licence that forbids derived valuations (we read the terms before we model); a model that is worse than the incumbent (three months of silent validation before any claim); no traffic for Scoutline (it does not grow without the weekly list and the Undertow cards); scope creep ("just one more league": seven competitions are locked until validation is published); and the founder's time, which is the real constraint on everything above.
| Name | Meaning |
|---|---|
| Bonaventure | A ship's name: good fortune, good voyage. The umbrella. |
| Keelson | The inner beam that strengthens the keel. The corporate edition that sits on the platform. |
| Reach | A point of sail; also the act of reaching a customer. |
| Siftah | Turkish shop talk for the first sale of the day. |
| Undertow | The current beneath the surface. The news under the news. |
| Spindrift | Spray torn from a wave crest by the wind. The surface twin of the undertow. |
| Scoutline | A scout's line: the value curve of a player, drawn by a model instead of a rumour. |
| Bergovich | The music studio's name. Just a name. |
| Çırak | Apprentice. |
| Kayık, Sandal | Rowing boat, dinghy: the Reach package names, smallest first. |
| Bridge | Where the ship is steered from: the internal control panel. |
Contact: [email protected] · bonaventurecorp.com
Company record: Bonaventure is being incorporated; the legal entity and company details will be added at incorporation. Until then nothing in this document is an offer, and every price is either a published introductory price (Reach) or an explicitly labelled hypothesis.
This document is generated from the internal structure document, decision log and plan, and regenerated when they change. Version 1 was produced on 31 October 2026; version 1.1 the same day after an editorial review (clearer product pages, status taxonomy, method note, layout fixes). If you find a claim here that does not match what you see in a product, tell us; that is a bug, and we fix bugs.