About HoundDog.ai

Deterministic context for engineers, coding agents, and privacy teams.

HoundDog.ai builds ProtoMap, a context engine and model harness for gRPC and Protobuf, and the Privacy Code Scanner for privacy teams that need code-level evidence in their RoPA, PIA, and DPIA workflows.

Book a Demo Explore ProtoMap

ProtoMap By HoundDog.ai

New chat UserService one hop out ···

Ask ProtoMap about your code and data List all gRPC services Which services call <RPC method>? What is the blast radius of changing <field name>?

What calls UserService, and what does it call?

Thinking…

2 graph queries, 1 workspace view

UserService has 479 callers and 3 callees, one hop out:

It lives in protomap-test-golang, with 6 methods.Most callers use GetUser.It calls AuthService, SessionService, and EmailService.

Shown in the workspace Service UserService

What calls UserService, and what does it call? Ask about your code and data…

Opus 5.5 · High

Services Search services, methods, and fields

20 services

ServiceMethodsCallers

Service AuthService 4 1,000

Service CartService 3 2

Services name: UserService reach: Callers and callees (1 hop)

Callers Service AccountService Service BillingService Service CheckoutService Service ReviewService 1–4 of 479 total

479

Repository protomap-test-golang Service UserService Method GetUser

Callees Service AuthService Service SessionService Service EmailService

Service acme.users.v1.UserService Methods

MethodRequestCallers

Method GetUser Message GetUserRequest 412

Method UpdateUser Message UpdateUserRequest 61

Method ListUsers Message ListUsersRequest 24

Refreshed on every pull request Same input, same output

Our Mission

Precise context for large codebases, for people and for coding agents

We give engineers and AI coding agents deterministic gRPC and Protobuf context on codebases beyond 200,000 lines of code, and help privacy and compliance teams prevent risks early in development rather than document them after the fact.

Engineering teams already use AI agents to generate code, review it, find vulnerabilities, and, when compliance requires it, draft data flow maps. For small codebases under 100k lines of code, that approach holds up. At larger scale, cost, speed, and the need for deterministic evidence become the bottlenecks that decide whether AI assistance keeps delivering value or breaks down.

Two audiences, one bottleneck

Why precise context matters at scale

AI agents now write code that easily passes 200k lines. Vibe coders and solopreneurs ship features at a pace that used to take whole teams. The bottleneck has shifted: it is no longer how fast you can produce code, but how reliably an AI agent can reason about code that already exists.

For engineering and AI-assisted development

Whether AI generates a greenfield project or makes incremental enhancements, every prompt to update a service or API forces the agent to rediscover what the code already knows:

Cross-service relationships across the repo
The fields used in every API call
The APIs called by every service

On a small codebase this is cheap. At scale it becomes a real drain:

Minutes of grep across thousands of files
Ad-hoc bash scripts that change run to run
Non-deterministic output that erodes confidence in every PR

For privacy and compliance

Using AI agents to generate data maps for RoPA documentation, or to validate PIA and DPIA reviews in development, creates three structural problems:

A cost and time drain, impractical for everyday compliance work
CI workflow integration that breaks down at scale
Non-deterministic output: the same prompt against the same codebase produces different maps on different runs

That last one matters most. RoPA and PIA evidence has to stand up in front of regulators and auditors. Output that changes from run to run puts a question mark on every claim.

What we build

One deterministic graph from code serves both audiences

For engineering teams & AI coding agents

ProtoMap

ProtoMap is a context engine and model harness for gRPC and Protobuf. It maps every service, message, and field across your organization’s code, updates with every commit, and needs no AI tokens.

Explore ProtoMap Benchmarks MCP Server Free on GitHub

For privacy & compliance teams

Privacy Code Scanner

Code-level dataflow intelligence that detects privacy risks and automates GDPR data mapping, with code-based evidence for your RoPA at development speed.

Explore the Privacy Code Scanner Free on GitHub

The right setup

AI is powerful. Overreliance on it for every task is not the answer.

Anthropic's own guidance for rolling out coding agents on large codebases says it directly: teams need to "invest in codebase setup to see better results." The recommended setup uses MCP servers and skills to give agents the right context: not to maximize how much the agent does on its own, but to make the code it generates safer and more accurate while controlling the cost and time it burns.

That is the gap HoundDog.ai fills. ProtoMap runs on every prompt, every PR and every commit, and gives the agent the cross-repo, cross-service, field-level context it cannot reliably reconstruct on its own. The model reasons; the context engine supplies the facts.

Anthropic best practices

How Claude Code works in large codebases

See it in action

ProtoMap demo

The Founding Team

Built by operators who lived the problem

Amjad Afanah

CEO & Co-founder

Amjad is a serial entrepreneur with a rich background in cybersecurity and developer productivity. He led his first company, DCHQ, a cloud management startup, to acquisition, and later founded APISec.ai, which developed one of the first API security scanners. Before founding HoundDog.ai, Amjad served as VP of Product at Cyral (acquired by Varonis). Before Cyral, he led product management at Cruise building developer productivity tools and the cloud platform underpinning the autonomous vehicles.

Joohwan Oh

CTO & Co-founder

Joohwan is an experienced engineering leader skilled in both scaling services for millions of users and developing new software from scratch. Before joining HoundDog.ai, he was a founding engineer at Aktos, a FinTech startup focused on modernizing the accounts receivable management industry. Joohwan has also led key projects at Meta, Amazon, and Instacart. Today he oversees the development of HoundDog.ai's cloud platform and the AI workflows that significantly enhance the scanner's accuracy and coverage.