Q3 intake · 1 of 2 slots open
Bengaluru · working across SF, NYC, London, Singapore
an ai-native software studio
Seven hundred and twenty hours. Then it ships.
Agents run the delivery loop — spec, build, test, deploy, watch. Two senior engineers hold the bar on every merge. That is why thirty days is a date on a contract here, and not an ambition.
- brief → spec T+000 · day 01—03
- agent-driven build T+072 · day 04—21
- polish + integration T+504 · day 22—27
- handoff + ship T+648 · day 28—30
A 720-hour delivery window divided into four phases: brief to spec, hours 0 to 72; agent-driven build, hours 72 to 504; polish and integration, hours 504 to 648; handoff and ship, hours 648 to 720. The current cycle sits at hour 336.
- from $15K
- fixed price, quoted before kickoff — no hourly meter
- 15+
- products shipped across regulated and consumer verticals
- 100%
- yours — repo, agents, cloud and keys in your accounts
- 2 / cycle
- engagements accepted at a time · founders only
posture
A studio where agents do the typing and humans hold the bar. Fifty-plus years of cumulative engineering, two engagements at a time, and a default we have turned work away to protect: whatever you tell us stays in the room.
- Not a dev shop.
- We don't sell headcount by the month. We sell a shipped product on a date.
- Not an offshore vendor.
- The first call is with the founder and the engineer who would lead your build.
- Not an account-managed agency.
- Nobody writes you a proposal and then disappears before the work starts.
the arithmetic
Your agency quoted
six months. You don't
have six months.
Bootstrapped founders aren't short on ideas. They're short on runway. The traditional model — scope phases, weekly check-ins, slow handovers — was built for a world where engineers were the bottleneck.
They aren't anymore. kaedax is what happens when you accept that the agents are the engineers now, and the humans are here to make the taste calls.
Six times the pace, at the same depth — because the volume work is done by agents that don't sleep, wait on a standup, or context-switch to another account.
the 720-hour cycle
What thirty days
actually looks like.
Four phases, four sets of artifacts, one fixed deadline. No Gantt theatre and no mystery about where the hours went.
- T+000 → T+072 Day 01 — 03
Brief → spec
You talk to a human. We talk to scope.agent. By day three there is a signed spec, an ADR log and a UX flow — not a forty-slide proposal.
- spec.md
- adr/
- ux/flows.fig
- T+072 → T+504 Day 04 — 21
Agent-driven build
Build, QA and deploy agents run on a tight loop. Two human engineers steer, review every PR and own the hard judgement calls. You watch the cycle log in real time.
- main · 87 PRs
- vitest · 91% cov
- preview deploys × 14
- T+504 → T+648 Day 22 — 27
Polish + integration
The unglamorous week. Edge cases, error states, onboarding copy, perf budgets, the analytics you forgot to ask for. This is the part shops skip.
- lighthouse 99+
- sentry armed
- stripe live
- T+648 → T+720 Day 28 — 30
Handoff + ship
Production cutover. You get the repo, the agents, the runbooks and the dashboards. We are on call for thirty days after, with no extra invoice.
- prod live
- runbook.md
- 30d on-call
live cycle log
What the middle of a build actually sounds like: agents reporting in, a human getting paged when something is ambiguous, and a cutover that lands with hours to spare.
streamed from a kaedax build · #027
the stack
Six agents.
One delivery loop.
Each agent owns one part of the cycle. None of them try to be the whole team. The humans do what humans are still better at: taste, judgement, and the awkward call.
- 01 scope.agent brief → spec
- Ingests your founder brain-dump, runs it through clarifying questions, drafts a working spec, and flags ambiguity before it becomes rework.
- spec.mdADR draftingopen-question log
- 02 build.agent module-level engineering
- Owns modules end-to-end — schema, API, UI, tests, docs. Opens PRs against a human reviewer. Won't merge to main without a green QA pass.
- repo writesPR draftsself-review
- 03 qa.agent tests, perf, regression
- Generates tests from the spec, not from the code. Runs the suite on every PR. Tracks coverage, Lighthouse, and a perf budget you'll actually feel.
- vitest genplaywright runsperf budget
- 04 deploy.agent preview → prod cutover
- Provisions preview environments on every PR, handles env vars, runs migrations safely, and executes the production cutover with a rollback plan.
- vercel / flymigrationsrollback plan
- 05 monitor.agent sentry · axiom · uptime
- Wires telemetry from day one. Triages incoming errors, deduplicates them, opens issues in the repo, and pages a human only when it matters.
- sentryaxiomcron pings
- 06 ops.agent standups, status, handoff
- Writes the daily standup, the weekly status, the runbook and the handoff doc — so the team spends zero hours on agency theatre.
- daily digestrunbookweekly note
the guardrail is the product · live
Agents that run your
product — and stop
when they should.
Not a chatbot bolted on the side. The agents we ship operate inside the product, call real tools, and pause for a human on anything that moves money, data or infrastructure. When policy says no, they refuse — and say why.
· eval-gated · human-approved
liveRefund order #4471 and notify the customer
replay a run
- Streamed plan, then MCP tool calls
- You see what it is about to do, and exactly what it touched.
- Human-in-the-loop approval
- No irreversible action runs without a sign-off from a person.
- Eval-gated and policy-aware
- The same refusal layer guards every vertical demo we publish.
Also live in every product demo — look for the ✦ copilot.
selected engagements
Six recent cycles.
Fintech, healthtech, ecommerce, insurance, B2C and agent products — anonymised under NDA. The engineering shape and the outcomes are as delivered.
- 01 TALLOW An end-to-end personal-finance agent for solopreneurs — perception, reasoning, memory, tools, and an eval harness — shipped as a product, not a demo. TALLOW set out to build a 'personal CFO' agent for solopreneurs: it ingests bank feeds, classifies transactions, surfaces decisions, and answers natur… AI · Consumer agent product Lisbon · PT 1 cycle · 720h open →
- 02 LATTICE An underwriting console for an SMB credit fintech, built and shipped in a single cycle. LATTICE needed to replace a spreadsheet-driven credit committee with an internal underwriting console that pulled bureau data, ran their proprietary s… Fintech · SMB credit Singapore · APAC 1 cycle · 720h open →
- 03 AURORA An AI agent module dropped into an existing B2B SaaS, behind a feature flag, with an eval harness that gated every PR. A workflow SaaS with 1,200 enterprise customers wanted to ship an AI assistant inside their product without disrupting the existing surface or risking… AI · Embedded feature Toronto · CA 1 cycle · 720h open →
- 04 CADUCEUS A clinician-facing chronic-care platform with patient intake, structured encounter notes, and an AI scribe that earns clinician trust. CADUCEUS needed to ship a working clinician console — intake, scheduling, encounter notes, an AI-assisted scribe, and an audit trail — for a pilot wit… Healthtech · Chronic care Bay Area · USA 2 cycles · 1,440h open →
- 05 PULSE A community-first creator platform that turned a 4,000-person waitlist into a launch, with the agents quietly running the live ops layer. PULSE is a creator-community product — a hybrid of a paid newsletter, a member-only feed, and a private chat. The founders had a 4,000-person waitlist… B2C · Creator economy Berlin · DE 1 cycle · 720h open →
- 06 BOUGH A direct-to-consumer storefront with a made-to-order configurator, replacing a Shopify build that had outgrown the platform. BOUGH sells solid-oak furniture made-to-order. Their Shopify store buckled at the configurator step — too many options, too many SKUs, too much pricin… Ecommerce · DTC home London · UK 1 cycle · 720h open →
Identifiers anonymised · published with explicit written consent
All engagements →terms
A studio, not a shop.
Headquartered in Bengaluru. Curated intake, two engagements per cycle, founders only. This is what every engagement looks like before a line of code is written.
- 01
Mutual NDA before scope
Nothing about your product, your team or your conversations leaves the room without your written consent. We have turned away engagements rather than weaken this default.
- 02
Code lives in your cloud
Repo, CI, secrets and deploy keys all sit in your accounts, never ours. We are guests on your infrastructure for the duration of the cycle, and we leave it cleaner than we found it.
- 03
Regulated-vertical posture
Scoped IAM, customer-managed keys, signed audit trails, and an eval harness for any AI output. Table stakes for fintech, healthtech and insurance work — and where we expect to spend extra cycle time.
- 04
A human on every judgement call
Two senior engineers review every PR. Founders sign the ADRs. The agents do the volume, humans hold the bar, and we decide together when the bar should move.
the posture we bring to each vertical
- Fintech PCI-aware controls · audit-grade trails →
- Healthtech PHI handling · ephemeral inference →
- Insurance Regulator-aware SLAs · evidence trails →
- Ecommerce PCI · DPDP · GDPR-respectful defaults →
- Consumer Moderation defaults · trust and safety from day one →
Plus AI and agents, marketplaces, internal tools, proptech, legaltech and education — all eleven verticals →
For the rest — the architecture, the human moments, the things we won't take on — read the full process.
Read the full process →objections
Things founders
ask first.
If your question isn't here, bring it to the scope call. We would rather answer it directly than write around it.
01 Is thirty days actually enough?
For a focused MVP, a contained AI feature, or a domain-shaped product — one fintech surface, one healthtech workflow — yes. The agent loop is designed around that exact scope. For multi-product platforms it isn't, and we tell people so on the scope call. We do not take builds we can't ship.
02 What if the agents write bad code?
Two senior human engineers review every PR. Nothing merges to main without a human approving the change and a green test suite. The agents do the volume; the humans hold the bar. You meet both on day one, before any code is written.
03 Do I own the code, the agents, and the prompts?
Yes. Entirely. Repo, agents, prompts, runbooks, eval harness, deploy keys. You leave the cycle with all of it, and we have no continuing access to anything once the post-launch on-call window ends. We do not gate anything behind a kaedax dependency.
04 How do you handle confidentiality and IP?
Mutual NDA before any scope conversation. Code lives in your repo, in your cloud, under your accounts — never ours. Secrets stay in your vaults. We publish case studies only with explicit written consent, and we anonymise client identifiers by default.
05 Can you work on regulated products in health, finance, or insurance?
Yes. Most of our work sits in those verticals. We bring the security posture — encrypted at rest, scoped IAM, signed audit trails, an eval harness for any AI outputs — and we partner with your compliance counsel on the certifications. We are an engineering partner, not an auditor of record.
06 Which models and frameworks do you use?
Defaults: Claude as the planner model, MCP for tool contracts, LangGraph where we need explicit graph orchestration and narrow direct code where we don't. pgvector for memory in most builds, because we prefer the ops simplicity of Postgres. Inngest or Temporal for long-running jobs. We do not maintain a buffet of 'we work with everything.' We have opinions, we ship with them, and we deviate when there is a real engineering reason. Switching defaults mid-cycle is a deliberate ADR, not a slide.
07 What's the engagement size you work with?
Shared on the scope call once we understand what you are building. The cycle unit is fixed at 720 hours; the number of cycles depends on the product. We don't publish pricing because every engagement is shaped to its specific work, and because the founders we want to work with care less about a number than about who is actually building.
08 Who shows up on the call?
Nanthana Rajendran, who founded kaedax, plus the engineer who would lead your build. Not a salesperson, not an account executive. If we can't help you we say so on the same call, and we usually point you at someone who can.
field notes
What we learn, written down.
- 06 Jun 2026 MCP is the right contract for agent tools Tool calling done as ad-hoc per-app function definitions is a fragility tax. Model Context Protocol is the contract layer the agent-product economy needed. Here is why we default to it, and the one case where we don't. engineering
- 02 Jun 2026 Why 720 hours is the right delivery window Six months is a hedge, not an estimate. Two weeks is bravado. Thirty days is the only window that respects both founder runway and engineering reality. manifesto
- 30 May 2026 The refusal layer is the product Most agent demos fail at refusals, not at execution. For agents that touch money, health, or sensitive data, what the agent will not do is a sharper product surface than what it will. A note on building refusal-first. manifesto
- 28 May 2026 The agent stack we use to ship in 30 days Six agents, one human-shaped loop. Scope, build, QA, deploy, monitor, ops — how each one earns its keep and where we deliberately don't trust them. engineering