Abhishek Uniyal

Updated Jun 2026

Currently — Draftly · Dexter

Forward-deployed product engineer

I embed with founders and ship the system the product actually needs.

Deep in AI-native systems when the problem calls for it.

Abhishek Uniyal
150+
B2B clients scaled
agent platform SDK, US EV startup
3 DBs
in production
text-to-SQL: Postgres, MySQL, Mongo
95%
zero-token
deterministic AI-agent gate

What brings you here?

Pick whichever one sounds like you — that's your way in.

I'm hiring

Abhishek is a product engineer who builds at the founding level. He owns the whole system, from scoping the real problem and designing the architecture to writing the integration and getting it to production. He has shipped an agent platform serving 150+ B2B clients, a deterministic gate that blocks unsafe AI-generated code, and a plain-English engine that works on production databases.

Selected workAboutAgent platform case study

I need contract help

Abhishek works with teams two ways: forward-deployed, or on a full product build. He starts from the customer problem and the data, not a specific model, and measures the work by what ships and survives. Recent builds include DeepQuery, Dexter, and the SynergyBoat agent platform.

Selected workStart a conversation

I want to read your thinking

Abhishek writes about the engineering that gets AI into production: managing context budgets, building deterministic gates, and designing multi-agent platforms, plus the gap between a demo and a system that survives real load. Most of his writing is on Medium.

WritingNotes

Recently

01 Selected Work

Selected work

All work →

SynergyBoat · Founding Engineer & CTO · 2026 – present

Draftly, a multi-agent AI content platform

Content teams needed to ship blogs, landing pages, and short videos without a studio. Built Draftly: a planner splits each piece into nine stages and routes every step to the cheapest model that can do it, producing both copy and short-form video in one system. Live at draftly.synergyboat.com.

Next.js · Bun · Hono · Postgres + pgvector · BullMQ · Remotion · MCP

→ Live

SynergyBoat · Founding Engineer & CTO · 2025 – present

Dexter, an enforcement layer for AI coding agents

AI coding agents introduce boundary violations that review misses. Built Dexter: a pipeline of deterministic AST, architecture, and pattern gates that block non-compliant code before it lands, running 95% of validations with zero LLM tokens. Live at dexter.synergyboat.com, with a VS Code extension.

TypeScript · ts-morph · AST analysis · VS Code extension

→ Live

SynergyBoat · Founding Engineer & CTO · 2024 – present

HirePulse, an agentic recruiting platform

Manual candidate sourcing does not scale. Built HirePulse: agents source candidates, score them on five factors, and run first-round voice-screening interviews, so a small team can run a full pipeline around the clock. Live at hire.synergyboat.com.

TypeScript · Hono · BullMQ · Supabase + pgvector · Plivo · Deepgram

→ Live

SynergyBoat Solutions · Founding engineer · 2024 – present

SynergyBoat agent platform SDK

A US EV startup scaled to 150+ B2B clients with ~40% lower dev cost and extended runway on a $2M seed.

TypeScript · MCP · isolated-vm · Deno · Redis · PostgreSQL · BullMQ

SynergyBoat · Founding engineer · 2024 – present

MCP toolkit monorepo

Cut net-new boilerplate across SynergyBoat's AI products by extracting AST editing, token-budgeted context, and query-intelligence into one shared toolkit every internal agent now depends on.

TypeScript · ts-morph · pnpm · Turborepo

SynergyBoat · Founding Engineer & CTO · 2024 – present

DeepQuery, plain-English access to your databases

Teams sit on databases their non-technical people cannot query. Built DeepQuery: it discovers a schema and answers plain-English questions across Postgres, MySQL, and Mongo. We run it internally today and are shaping it into a product so clients can query their own business data the same way.

TypeScript · PostgreSQL · MySQL · MongoDB · OpenAI

02 Writing

Writing

Read the archive →
03 Notes

Notes

All notes →
04 How I Work

How I work

AI is a value-add, not a reason. The product still has to make sense to the customer without it.

I build the system a product actually needs, then stay until it works in production. Seven years across YC-backed startups and founding-stage teams taught me that the gap between a demo and a system is everything the pitch deck leaves out: real users, production load, the constraints nobody scoped. I start from the customer problem and the data, not the model. The work is technical; the reason it exists is not.

Forward-deployed and product-engineering work with founders shipping AI into production. Selective fractional-CTO too.

Open to forward-deployed, product-engineering, and fractional-CTO conversations.

Planner and workers diagram A central planner node surrounded by six worker nodes connected by spokes — a visual metaphor for multi-agent orchestration. Workers are labeled with primitives from the author's work: scraper, ast-edit, sandbox, text-to-sql, mcp, and eval. scraper ast-edit sandbox text→sql mcp eval planner
05 Contact

Contact

If something here made you think "I want to work with this person," the fastest way is an email.

Or read more about me · Contact.