Built From Inside City Hall

Was your last council packet 460 pages long?

Built by a sitting city councilmember, CivicAide is for people who step up to serve their communities, especially part-time officials balancing public service with work, family, and everything else. It turns that packet into a brief written for you, not the whole dais: what each item is, what it costs, what changed, which items touch the platform you ran on, and what's worth asking before the vote. Every claim is cited or absent.

See What It Does →Request a Sample Brief

Where We're Focused

What's Real Today

The packet lands on Friday. The vote is Wednesday. This is the part in between.

CivicAide generates council briefs for a real city today, from the official meeting packet, before the meeting happens. Not a demo. Not a roadmap. The features below are running now, or honestly labeled when they aren't.

Live

Council Briefs

The official meeting packet — often 200-plus pages — becomes a brief a member can actually prepare from: what each item is, what it costs, what changed, and what's worth asking. Every claim traces to a page in the packet or it doesn't appear.

Live

Developments, Not Documents

The brief tracks an item's path from committee to council, flags what changed since the last time it appeared, and stays quiet when a routine item contains nothing material. Silence is a feature — it's what lets you trust the flags.

Live

On Your Radar

The staff report is written for everyone on the dais. Your brief opens with a private section flagging which items touch the priorities you ran on, with a question worth asking when an item cuts against them. It stays silent when there's no real connection, and no one sees it but you.

Live

The Whole Tax Bill

Your residents don't just fund city hall. Schools, county, parks, library, township: every overlapping taxing body is profiled in cited, human-approved snapshots, so you can see what's happening across the whole tax bill, not just the city's slice.

Live

Audio Summaries

Every brief gets an audio version for the commute or the dog walk. Each recording is transcribed back and checked word-by-word against its own text before anyone hears it — a fidelity gate, not a disclaimer.

In testing

PolicyAide

Multi-agent policy research for the bigger questions: enter a topic, get a cited policy brief where competing options were stress-tested through structured debate before reaching you. In testing with real sessions; not yet generally available.

Explore CivicAide in depth →

How It Earns Belief

It will never promise it's never wrong.

It promises its errors are visible, citable, and structurally harder to repeat. An official puts their name on what they say at the dais — a tool that briefs them has to be built for that standard, not for a demo.

Cited or absent

Every claim in a brief traces to a source — a packet page, a public record — or it doesn't appear. No confident filler.

Human review gates

A sitting councilmember reads and approves real outputs before a feature ships. Features that fail that reading don't ship until they pass it.

Silence as a feature

When a routine item contains nothing material, the brief says so briefly and moves on. A system that flags everything is a system you stop reading.

Verified accounts

PolicyAide is built for elected officials and municipal staff, and accounts are verified — a government email verifies instantly; everyone else is confirmed personally against public rosters. Stated as a trust signal, not a wall.

Why This Exists

The expertise is in the building. The hours aren't.

The same planner reviewing a 47-page environmental impact study is also answering phones, attending three committee meetings, and trying to update a comprehensive plan that's been outdated since 2018. The part-time councilmember voting on all of it has a day job and a 200-page packet that landed five days before the vote.

Meanwhile, the data that should power better decisions sits scattered across systems that don't talk to each other, half of it in PDFs. Cities pay five figures a year for records-request software that is, at its core, a form, a queue, and a deadline tracker — and thousands of smaller municipalities can't afford even that.

AI will change how municipal work gets done. CivicWork exists so those changes are made by cities themselves, deliberately and transparently — starting with the basic work of understanding what is before the council.

Part-time officials, full-time workloadCapacity gapsFragmented data systemsCompressed prep windows

Frameworks for Saying No

Most AI vendors sell what's possible. We start with what's appropriate.

Before building any tool, we ask two questions: Can we verify that it works? And does deploying it build or erode the trust a community needs? Together, the Verifiability Framework and Trust Stack form a diagnostic system for responsible municipal AI.

Framework 01

The Verifiability Framework

One question: Can we verify this? If you can define success criteria and automatically evaluate outcomes, the task is an automation candidate. If you can't, AI should augment human judgment, never replace it. And when a use case is mixed, decompose it, automate what you can, keep humans on the rest.

Verifiable → Automate

Permit completeness checks, document classification, data validation, compliance verification. Clear criteria, fast iteration, measurable outcomes.

Mixed → Decompose

311 triage, public chatbots, hiring, inspection scheduling. Separate the automatable components from the parts requiring human judgment.

Non-verifiable → Augment only

Budget priorities, policy tradeoffs, community needs, accountability decisions. AI expands what you know. Humans retain authority over who decides.

Read the full framework →

Framework 02

The Trust Stack

Four layers of trust, each building on the last. Layers 1–2 are built with technical tools: audits, testing, metrics. Layers 3–4 require democratic process: deliberation, community input, accountability. The common failure: trying to solve Layer 3–4 problems with Layer 1–2 tools.

Process TrustTechnical

Did it follow the rules?

Outcome TrustTechnical

Did it work?

Representation TrustDemocratic

Does it reflect us?

Sovereignty TrustDemocratic

Do we still control this?

Read the full Trust Stack →

“AI should expand what you know, not replace who decides.”

These frameworks give municipal leaders structured language for evaluating AI proposals, and principled grounds for declining when a deployment doesn't fit, without sounding like they're against technology.

We've worked with U.S. Digital Response (USDR) on AI use case discovery across Elgin city departments, using the Verifiability Framework and Trust Stack as diagnostic tools to identify where AI helps and where it doesn't.

Built From the Inside

“I started building CivicAide because I needed it. A part-time councilmember with a day job, trying to get through 200-page packets before the next vote. It was a Coda doc connected to a few LLMs. Then frontier models got good enough to do real policy analysis. Then agent frameworks matured enough to orchestrate it. The tools kept getting better, so the ambition kept growing.”

Dustin Good is a sitting at-large city councilmember in Elgin, Illinois, second term, 4.5 years in office. CivicWork grew out of the problems he encountered firsthand: too much data, too little time, and a growing conviction that local government shouldn't have to wait for vendors to solve problems practitioners already understand.

4.5 yearsin elected office

2 termsas at-large councilmember

SpeakerIML & City AI Connect conferences

Our Approach

How we think.

Practitioners first

This wasn’t designed from a research lab or a consulting firm. It was built from inside a municipal building: from the meetings, the packets, and the cross-departmental workflows that make local government actually function. The tools reflect actual workflow, not a theory of it.

Automation before AI

Not everything needs a language model. Sometimes a well-structured automation does the job. Just as important: CivicWork helps municipalities say no to AI where it doesn’t belong. Staff are getting pitched AI solutions for everything, and having a principled framework for declining, not out of fear but out of clarity, is as valuable as knowing where to deploy.

Own the data layer

When a municipality wants to leave a software vendor, they often discover their own data (years of records, workflows, and institutional knowledge) can’t come with them. Agent-readiness means making public data accessible, portable, and structured, not just for humans, but for the AI tools that will increasingly help staff do their jobs. That’s not a technology problem. It’s a data ownership problem, and it’s what we’re building toward.

Build on the best, contribute what’s missing

We don’t rebuild what the AI industry has already built well. The agent infrastructure is maturing and we build on it. What we contribute is the accountability layer often missing from general-purpose AI infrastructure: citations, review gates, and traceability designed for public service. Currently built on Anthropic’s infrastructure and designed so cities are never locked to a single provider.

Open Source Tools

What's open today.

Two tools are open source under Apache 2.0 today, usable and forkable by any municipality. The CivicAide platform itself is built in the open, with components released as they mature.

Claude Plugin

Municipal Governance Plugin

Eight skill modules for Claude Desktop and Claude Code: ordinance analysis, meeting prep, policy research, budget review, constituent communications, agenda packet synthesis, intergovernmental scanning, and vendor contract evaluation. Each module includes built-in analysis boundaries that disclose what a single AI instance can and can't responsibly conclude.

View on GitHub →

WebMCP + Chrome Extension

Municipal WebMCP

WebMCP configurations and a Chrome extension that give AI agents structured access to public legislative data. Covers Legistar (Granicus) meeting and legislation records and Municode (CivicPlus) codified law across 3,300+ municipalities. Public data should be easy to access programmatically, not just through a web browser.

View on GitHub →

Apache 2.0Free to use · Free to fork · Built for municipalities

Live Now

Your city council agenda, explained.

Council agendas are public documents. Understanding them shouldn't require a law degree. CivicBrief takes an agenda PDF and turns it into plain-language briefings you can actually use, in your language, in your preferred format.

Pick the items that matter to you, choose between a written summary, Q&A, audio, or visual format, and get a briefing built for residents, not attorneys. If someone already asked about the same item, it loads instantly from cache.

Try CivicBrief →

Upload or browse

Drop a city council agenda PDF or pick one that's already been uploaded from the library below.

Pick what matters

Select agenda items and choose your format and language.

Get your briefing

Plain-language summary, Q&A, audio, or a visual you can share.

Multilingual (English, Spanish, Polish) · Four output formats · Cache-first for instant results · AI-generated, always attributed

The brief is the pitch.

If you're an elected official or municipal staff member, the fastest way to evaluate CivicAide is to read a real brief for a real meeting. Ask for one. If you're a resident, try CivicBrief right now.

Request a Sample Brief →Try CivicBrief →Run the Governance Assessment View on GitHub