Permit, intake and casework automation

AI agents for government intake, casework and permits, with staff making every decision

Agents for intake, case notes, permits and correspondence that do the routine steps, follow your approval rules and keep a full audit trail. Staff make the decisions.

Free · about one week · view-only · no obligation

View-only access your IT administrator approves and removes. Nothing in your systems changes.

AI agents for government intake, casework and permits

Short answer

We build AI agents for public agencies on Microsoft 365, Power Platform and Azure that take on high-volume mandated work: intake, case notes, permit checks and correspondence. Every agent has a named owner, approval rules, logging and an off switch, and staff make the decisions. A pilot agent takes 6 to 8 weeks and typically costs $25K to $50K.

Starting points

Where AI agents for government earn their keep

Path A“Applications arrive incomplete and staff chase the gaps.”An intake agent checks completeness, requests missing items and opens the case.See intake
Path B“Caseworkers write notes in the evening.”Drafts of case notes and summaries from meetings, calls and documents, for staff to approve.See case notes
Path C“The correspondence backlog keeps growing.”Letters and emails drafted in the agency’s voice and routed for approval.See correspondence

The cost of waiting

Agents are arriving faster than the controls around them

91%of organizations only find out what an AI agent did after it acted.Source: Cisco, AI agents and cybersecurity
37%of organizations can revoke an AI agent’s credentials, and only 30% keep tamper-proof logs of what agents did.Source: Palo Alto Networks 2026 Identity Security Landscape, via Help Net Security

An agent without an owner, a log and an off switch is a liability.

Ours ship with all three, and they act inside your approval rules.

What it really is

An agent is a new member of staff. It needs a role, a supervisor and a record of what it did.

The software is the smaller part. The work is defining what the agent may do and proving it did only that.

Defined roleA written scope of what the agent may and may not do.
Named ownerA person in your agency accountable for it.
Approval rulesPeople approve anything that affects a resident.
Audit trailEvery step logged in your own Microsoft 365.
Off switchDisable it in one step, any time.
ReviewedAccuracy and backlog reported on a set schedule.

Your options

Scripted automation, an agent platform, or a governed build

Agencies have automated routine work for years. Agents handle what scripts could not, and need more control.

Scripted automationAgent platform licenseGoverned agent in your own Microsoft 365 (us)
Unstructured documentsNoYesYes
Approval rulesScriptedConfigurableYour rules, with people approving decisions
Audit trailLogsVariesEvery step logged in your own Microsoft 365
Owner and off switchNot built inVariesNamed owner, off switch, review schedule
Runs onA separate platformThe vendor’s platformPower Platform and Azure you already license

What is included

Where agents help

Intake

Read applications and submissions, check they are complete, and open the case with the right data attached.

Case notes and summaries

Draft case notes and summaries from meetings, calls and documents for staff to review and approve.

Permits and licensing

Check applications against requirements, request missing items and prepare a decision for review.

Correspondence

Draft letters and emails in the agency’s voice, routed for approval before anything is sent.

Governed and supervised

Each agent has an owner, approval rules, logs and an off switch, and is reviewed on a set schedule.

Measured

Time saved, backlog and error rates reported for every agent, so you know what it is worth.

Our approach

One process at a time, proven before it goes live

Agents earn trust in shadow mode before they handle real work.

  1. Pick one processChoose the backlog with the clearest rules and the most volume.
  2. BuildThe agent, its approval rules and its audit trail, in your own Microsoft 365.
  3. Shadow modeThe agent drafts while staff still do the work, and we compare results.
  4. Go live and measureSwitch over when accuracy meets the agreed bar, and report monthly.

Our promise: no agent makes a decision that affects a resident. It prepares the work, and a person decides.

Governance, security and data handling

Where your data goes, and who stays in control

  • Inside your own Microsoft 365. We build in your Microsoft 365 and Azure environment, using the identity and permissions you already govern.
  • Exposure fixed first. An AI assistant sees whatever its user can see, so oversharing and unlabeled sensitive content are dealt with before anything is switched on.
  • Hosted in Microsoft Foundry on Azure. We use the model that fits the job: OpenAI, Anthropic or open-source models, deployed in Microsoft Foundry on Azure. Your data is never used to train them (see Microsoft’s data terms for Foundry). Anthropic operates its Claude models on Azure under its own commercial terms, and we show you which model and which terms apply before work starts.
  • People decide. Approval rules, audit trails and human review wherever an output affects a resident, a record or a decision.

What it runs on

Built on AI-powered managed services

Agents need running after go-live: monitoring, model updates, access reviews and reports. Our managed service does that alongside your security and licenses.

Run after go-liveOur AI-powered managed service monitors each system, keeps models and controls current, and reports every month. See managed services
Governed from day oneIdentity, labels and data loss prevention decide what AI can reach. See Microsoft security

Proof

Government work this builds on

Agents run on the same workflow platform as the systems we already build for agencies.

Current
Orange County Transportation AuthorityA grants management application with Power Automate workflows and Dataverse in GCC, with operations and maintenance through 2030.
Since 2024
Town of Hilton Head IslandPower Automate workflows across Finance, HR, Fire & Rescue and Legal, with monthly developer hours adding new flows.
Since 2021
Town of BlufftonApproval workflows built to the Town’s own business rules on governed SharePoint.

See our government record

The offer

One week, read-only, and a plan you keep

The AI readiness assessment shows what an AI assistant could find in your Microsoft 365 today, which uses are ready, and what each one needs before it goes live. The report is yours whether or not you build with us.

Exposure map

What an assistant could reach today: oversharing, permission sprawl and unlabeled sensitive data, ranked by risk.

Use-case shortlist

Three to five uses your agency could start with, scored for value, risk and readiness.

Plan and fixed price

The controls each use needs and a fixed-price estimate for the first build, ready for your procurement process.

  • Free, with no obligation
  • About one week
  • View-only: nothing in your systems changes
  • The report is yours to keep

Why free? It is how we scope a fixed price we can stand behind, and it shows you what to fix whether or not you hire us.

How it runs

Day 030-minute scoping call with the architect who would run the work.

Days 1–2Your administrator grants read-only consent. About an hour of your team’s time.

Days 2–4We review your Microsoft 365 and talk to the use-case owners you choose.

Day 5Findings session: exposure map, shortlist and fixed-price plan.

We reply within one business day.

Read-only Microsoft Graph permissions only, consented by your administrator and revoked at the end. No content leaves your Microsoft 365. NDA and data processing terms before any access.

Why agencies choose us

A Microsoft partner that builds and runs it

Government work since 2015150+ government orders for 34 agencies since 2018. See the record
Authorized for government cloudAOS-G for GCC High, Tier-1 Cloud Solution Provider, Solutions Partner for Azure (Data & AI, Infrastructure, Digital & App Innovation) and Modern Work.
Hosted in Microsoft FoundryOpenAI, Anthropic or open-source models on Azure, chosen per use. Your data is never used to train them.
We build it, then run itThe architects in the assessment build the system and operate it after go-live.
Microsoft Solutions Partner designations: Data & AI, Infrastructure and Digital & App Innovation (Azure) and Modern Work

Transparent investment

The assessment is free. Here is what the work costs.

Every agency is different, and the assessment gives you the firm number. You deserve a real range first.

EngagementTypical timelineTypical investment
Pilot agent: one process, shadow mode6–8 weeks$25K–$50K
Each further production agent1–3 months$20K–$100K
Multi-process deployment3–6 months$75K–$250K
Managed AI operationsMonthly$2.7K–$10.5K a month

Model usage, Power Platform licensing and training are in the estimate, not a change order.

Common questions

AI permit review and case management AI: questions agencies ask

Can AI review a document or application?

Yes, for the routine checks: an agent can confirm that every required field and attachment is present, compare stated values with the rules for that application type and list what is missing, citing the page. A member of staff reviews its findings and makes the decision.

Can AI read construction plans?

It can read plan sheets and extract what the intake checklist needs, such as sheet index, stamps, dimensions and notes, and flag missing sheets. AI permit review speeds up completeness checks; code compliance decisions stay with your plans examiners, who see the agent’s findings next to each sheet before they decide.

How can AI help social workers?

Mostly by giving back time spent writing: case management AI drafts case notes from the record, prepares letters and summarizes a file before a visit, working from the case management system you already use, and the caseworker edits and approves every word. Decisions about people stay with people.

What is agentic AI in government?

Agentic AI in government means AI agents that carry out steps of a process, such as checking an application, drafting a letter or updating a case, rather than only answering questions. AI agents for government need what any new member of staff needs: a role, a supervisor who approves their work and a record of what they did. Every agent we build has all three, plus an off switch.

Questions buyers ask

Before you decide

Will agents replace staff?

They take the routine steps off staff, such as chasing missing documents or drafting first versions. Decisions stay with people, and most agencies use the time to clear backlogs.

What if an agent gets it wrong?

It runs in shadow mode first, people approve its outputs, its error rate is reported, and it can be switched off in one step.

Will it work with our case management system?

If your system has an API or a Power Platform connector, usually yes. The assessment confirms it before you commit.

Who is accountable for an agent?

A named owner in your agency, supported by us. The owner approves its scope, sees its reports and decides when it changes.

Clear the backlog, keep the control

The free assessment finds the process where an agent would save the most time and prices a pilot.

AI agents for government intake, casework and permits