Policy Central
An open-source agent for writing and reviewing policy documents. Ask it to check a manual, adapt or revise a policy, or draft a new one. It finds clauses that conflict with or repeat your other policies, and the clauses a change affects. Each finding quotes both clauses, and each change waits for your approval.
Orlando PD’s body camera policy checked against CFA standard 32.02M: one wording error, quoted from both documents, fixed as a tracked change.
Works with: Word documents · PDFs, including scans · web pages · web search.
The beta is by invitationEach person gets their own link; nothing to install and no account. Write to support@policinglab.org for one.
Try it now
Opening to invited reviewers first
Who it is for
Eight people, eight checks. Pick one to see their situation, what they would type, and what comes back. The documents named are public.
1 of 8
Program lead: a new program needs a policy
- SITUATION
- The department starts flying drones to emergency calls next month and needs a policy. Florida’s drone law (F.S. 934.50) and the notes from the program’s planning meeting, with one of the department’s own policies (OPD 1138.7) to set the format.
- THEY ASK
- “We start a drone-as-first-responder program next month. Draft the policy in our format, using the meeting notes and meeting F.S. 934.50.”
- THEY GET
- A first draft laid out like 1138.7. Each section shows where it came from, and a click opens the notes or the statute at that line. A Word file with the same header, boxed sections and numbering.
2 of 8
Accreditation manager: before an accreditation visit
- SITUATION
- The assessor visits in March. Florida’s accreditation standard for body cameras (CFA 32.02M) against Orlando PD’s body camera policy (OPD 1140.12).
- THEY ASK
- “Our assessor visits in March. Does our body camera policy cover every item in CFA 32.02M, and what proof will we need to show?”
- THEY GET
- Four of the five items already match. The fifth, documentation, has one sentence written backwards, and the fix adds the missing “not”. The proof the assessor will ask for, and a Word file with the change tracked and the reason in the margin.
3 of 8
Special events planner: a big event is coming
- SITUATION
- The 2028 Olympics in Los Angeles. The federal planning checklist for major events (129 items) against the LAPD crowd management directive and the city’s fire code rules for special events.
- THEY ASK
- “The Olympics are 90 days away. What does our plan not cover yet from the planning checklist, and what should we sort out first?”
- THEY GET
- 64 of the 129 items in neither plan, 58 partly covered, 6 fully. What comes first: who leads when several agencies work together, then credentials, then training and drills. The drills line drafted into the directive, tracked in Word.
4 of 8
Legal advisor or policy unit: a new state law limits what you can do
- SITUATION
- Florida law requires police to support federal immigration enforcement. Florida Statutes chapter 908 against Tampa Police’s immigration policy (SOP 307.9).
- THEY ASK
- “Does our immigration policy conflict with Florida’s law on federal immigration enforcement, and what would we need to change?”
- THEY GET
- Four rules to change and two to confirm, first the ban on broad operations. It asks before making a rule less strict. The ban stays, with an exception for federal operations, tracked in Word.
5 of 8
Federal partners: joining a federal task force
- SITUATION
- Officers join a federal task force, wearing the department’s body cameras. The Justice Department’s body camera policy for task forces against Orlando PD’s (OPD 1140.12).
- THEY ASK
- “Our officers are joining a federal task force. Where does the DOJ task force body camera policy conflict with ours, and what do we need to change or agree with them?”
- THEY GET
- 10 rules to change, 7 to add, 6 to confirm. First, who releases task force video: the drafted change makes it a federal record, released only with DOJ permission, tracked in Word.
6 of 8
Policy unit lead: the law changes overnight
- SITUATION
- In September 2025 a Florida appeals court struck down the state’s open-carry ban, and open carry became legal statewide. The court’s ruling and the police chiefs’ memo on it, against six of a department’s policies, from bias-free policing to use of force.
- THEY ASK
- “Open carry became legal in Florida in September 2025. Which of our policies need updating, and what should they say?”
- THEY GET
- A plain answer: none of the six policies depends on the old ban. One line worth adding, to the bias-free policing policy: open carry alone is no reason to stop, search or arrest. The policy’s own PDF, with the line set into the page.
7 of 8
Neighboring agencies: a pursuit crosses the line
- SITUATION
- A pursuit starts in Orlando and crosses into Orange County. Orlando PD’s vehicle pursuit policy (1120.17) against the Orange County Sheriff’s pursuit order (8.1.7).
- THEY ASK
- “A pursuit starts in Orlando and crosses into unincorporated Orange County: where would an OPD officer and an OCSO deputy act differently?”
- THEY GET
- Ten differences, with both policies quoted, and one point both agencies must agree on: who commands once the pursuit is in the county.
8 of 8
Training lead: a new policy, every shift needs to know it
- SITUATION
- A new pursuit policy takes effect on Monday and every shift has to know it. Orlando PD’s vehicle pursuit policy (1120.17).
- THEY ASK
- “Make me a 10-question roll-call quiz on our pursuit policy, with the answers and the section each answer comes from.”
- THEY GET
- Ten questions, each with its answer and the section it comes from, as a Word file ready to hand out at roll call.
Free during the beta
Free during the beta. Your workspace is temporary and is deleted after an hour without use.
Privacy
- Kept
- What you type, your accept and reject choices, your feedback, the organisation and role you give if you choose to, and for uploads the title, the page count and the findings’ one-line summaries.
- Not kept
- Document text, full quotes, your address. There are no accounts. Uploads are deleted with the workspace, after an hour without use.
The app runs in The Policing Lab’s own AWS account; pairs of clauses go to the ranking model through OpenRouter. Don’t upload confidential drafts.
Open source
The code will be published under the AGPL-3.0 licence. Run it on your own machine with your own model keys, or read how it works.
Research
- Policy Central: Detecting Conflicts, Redundancy, and Similarity in Deployed Police Policy (Holly Baker, Michael Kuo and Kyana Pollas, 2026): the first Policy Central system, piloted with a police department, and the benchmark used to test it.
Who made it
Policy Central is made by The Policing Lab, a nonprofit in Miami that works with police departments on data and policy.
How well does it work?
General AI assistants are good for quick questions about a document. Policy Central is built for one job, reviewing policy: it reads the whole manual, checks policies against laws and standards, quotes both sides of every finding, and drafts the fix as a tracked change.
These are early results from a small test; a larger, independent evaluation is under way. In November 2026 we planted 10 contradictions in each of two public police manuals and asked each tool, on its default settings, to find where the manual contradicts itself.
1,596-page manual
| Tool | Found of 10 | False findings | Real issues we did not plant | Time | Cost per run | How much it read |
|---|---|---|---|---|---|---|
| Policy Central | 7 | 0 | 4 | 6 min | about $1.80 | every page screened; the likeliest conflicts read closely |
| AI coding assistant | 0 to 1 | 1 to 2 | 0 | 2 min | about $0.35 | opened under 1% of the lines; keyword searches for the rest |
| AI office assistant | 0 | 4 | 0 | 1 min | monthly licence | about 4%, by its own account |
455-page manual
| Tool | Found of 10 | False findings | Real issues we did not plant | Time | Cost per run | How much it read |
|---|---|---|---|---|---|---|
| Policy Central | 6 | 0 | 3 | 3 min | about $1.60 | every page screened; the likeliest conflicts read closely |
| AI coding assistant | 6 | 3 | 4 | 7 min | about $2.30 | every page |
| AI office assistant | 1 | 4 | 0 | under 1 min | monthly licence | not stated |
How we tested
- The manuals
- Two public US police manuals: the Los Angeles Police Department’s Department Manual (1,596 pages) and the Fort Worth Police Department’s General Orders (455 pages), as plain text.
- What was planted
- In each manual we altered 10 clauses so that each one contradicts another clause in the same manual: a duty reversed (“shall” to “shall not”), a time limit or an age changed, a definition turned around. Each tool was asked to find where the manual contradicts itself, with nothing said about planted clauses.
- How a finding counted
- “Found” is a strict count: a planted contradiction counted only when one finding quoted both the altered clause and the clause it was planted against. A script checked every quote word for word against the manual. A finding was false when the two clauses it quoted do not conflict when read in context. Findings we could not settle either way are left out of both counts.
- Real issues we did not plant
- Contradictions already in the manuals, which some tools found as well. One reviewer checked each one by hand against the manual.
- Runs and settings
- Each tool was run once or twice, on its default settings, and we wrote the planted contradictions ourselves. With stronger settings on the 1,596-page manual, the coding assistant found 1 in 7 minutes for about $2.90, having opened about 4% of the manual, and the office assistant found none in about 3 minutes, in each of two runs. Each also caught one planted contradiction against a different passage from the one we planted it against, which the strict count leaves out. Only default settings were run on the 455-page manual.
- Cost
- Model charges for one run, at list price. The office assistant’s cost is part of a monthly licence, so there is no per-run cost.
How we measured how much each tool read
- Policy Central. It breaks every manual into its sections and rules, and screens every one of them. It then reads closely the places most likely to conflict. Its record lists every comparison it made, and which ones it read closely.
- AI coding assistant. We ran it with its detailed activity log switched on. The log records every action it takes: each time it opens part of the file (with the exact line range) and each keyword search (with the words searched and the lines that came back). We added up the line ranges it opened. On the 1,596-page manual that came to about 300 to 400 of 44,497 lines with default settings (under 1%), and 1,681 lines with stronger settings (about 4%). Its searches also showed it matching lines from elsewhere in the file, but it never read the manual through.
- AI office assistant. We can’t see inside it, so after its answer we asked it how much of the manual it had read. With stronger settings it replied that it had read lines 0 to 799 of 22,248, about 3.6%, and had run an automated comparison over the rest; with default settings it said it had opened the first 800 lines. These figures are its own account.
- Why this matters. No keyword marks a planted contradiction: each is an ordinary-looking clause that disagrees with another one far away. A tool that searches rather than reads tends to miss them.
Feedback and contact
There is a feedback button inside the app. For anything else, write to support@policinglab.org.