AACPv1.4
[ AACP Protocol Draft · v1.4 ]// measured, open, MIT licensed
AACP // Agent Action Compression Protocol

Deterministic coordination for multi-agent systems

AACP is an open protocol and encoder framework that transforms natural-language agent instructions into typed, auditable coordination packets. Same input. Same output. Every time.

Open specification MIT licensed IETF Internet-Draft: draft-mackay-aacp-03 → Deterministic encoders Live API validated
Natural language. Varies on every run. Not auditable.
"Please retrieve the employee salary
records for the period ending 31 August
2024. I need all active employees, their
departments, cost centres, base salary,
any changes made this month, and pension
contribution rates. Return as JSON array."
AACP v1.4. Identical every run. Validated. Auditable.
FETCH|HR|return:HR-Agent|p:1|aacp:1.4
|res:emp_salary|period:2024-08
|filter:status=active|fmt:json

Token reduction (~23% measured) is a secondary benefit. The primary value is determinism and auditability.

$0.00
per coordination hop for known workflows
241
pre-validated community rules
59
coordination LLM calls eliminated per department day (across five workflows: payroll, IT provisioning, sales qualification, customer service resolution, and month-end close)

02 · Architecture

How AACP works

Natural language instruction
Workflow Encoder
rule-based, zero LLM cost for known workflows
FETCH|HR|return:HR-Agent|p:1|aacp:1.4|...
validated against schema before transmission
Receiving Agent
any model, any framework, any vendor
Structured result + audit record

For novel workflows without a pre-built encoder, a three-tier fallback routes the instruction to an LLM once, logs the result, and serves it from cache on every subsequent call. One LLM encoding call per novel pattern, reused indefinitely at $0.00.

03 · Comparison

Traditional vs AACP coordination

Same outcome: a monthly department report. Fundamentally different coordination.

Traditional coordination

HR Agent
Finance Agent
Sales Agent
Report Agent
"Please provide all active employee headcount by department for March 2026 including contractors..."
"Retrieve budget actuals vs plan for all cost centres for the period ending March 2026..."
"Score and summarise all open leads from Q1 2026 with BANT qualification status..."
3
Coordination LLM calls, non-deterministic, unvalidated

Report generated, eventually.

AACP coordination

HR Agent
Finance Agent
Sales Agent
Report Agent
FETCH|HR|return:RPT|p:1|aacp:1.4|res:headcount|period:2026-03
FETCH|FIN|return:RPT|p:1|aacp:1.4|res:budget_cc|period:2026-03
CALC|SALES|return:RPT|p:1|aacp:1.4|res:lead_score|rules:bant
0
Coordination LLM calls, deterministic, schema-validated

Report generated faster, auditable, identical every run.

Task reasoning stays fully active in both workflows. AACP coordinates; agents think.

04 · Principles

Why structured coordination?

01

Deterministic

The same workflow produces the same packet every time. Known workflows encoded at zero LLM cost, identical output on every run.

02

Auditable

Coordination messages become structured, machine-readable records. Every packet can be logged, replayed, and inspected without post-processing.

03

Reusable

Workflow encoders can be shared across teams, systems, and organisations. 241 pre-validated community rules available at launch.

04

Model-agnostic

Validated on Claude Sonnet 4.5, GPT-4o, GPT-4.1, and GPT-4.1-mini. The same packet, the same behaviour, regardless of which model receives it.

05

Efficient

Measured coordination token reduction of approximately 23% versus verbose English. Validated from live API usage_metadata, May 2026.

05 · Encoders

Workflow encoders

Rule-based encoders transform common business workflows into coordination packets with zero LLM calls and deterministic output. Eight encoders across six domains, each grounded in a documented real-world platform.

PayrollEncoder
HR6 hops

HMRC PAYE / UK payroll practice

ITEncoder
IT5 hops

Microsoft Entra ID provisioning

InvoiceEncoder
FIN3 hops

AP three-way match

ContractEncoder
LEGAL2-3 hops

NDA/MSA review

SalesEncoder
SALES5 hops

Salesforce Agentforce 2026

JMLEncoder
HR+IT6 hops

ConductorOne, Lumos, CloudEagle

CSResolutionEncoder
CS5 hops

Zendesk Resolution Platform

MonthEndEncoder
FIN6 hops

NetSuite Autonomous Close

from aacp.encoders.workflows.payroll import PayrollEncoder

enc = PayrollEncoder()
pkt = enc.fetch_employees("2026-03")
print(pkt.packet)
# FETCH|HR|return:HR-Agent|p:1|aacp:1.4|res:emp_salary|period:2026-03|filter:status=active|fmt:json

print(pkt.api_cost_usd)
# 0.0

06 · Community

Community rule library

241 pre-validated coordination rules across 7 domains: HR, Finance, IT, Sales, CS, Legal and Marketing. MIT licensed. Load locally. Zero API cost.

HRFINITSALESCSLEGALMKT
View on GitHub →

07 · Ecosystem

Built alongside existing agent standards

MCP (Anthropic / AAIF)

Tool access and external system integration. AACP structures the coordination payload that travels inside MCP messages.

A2A (Google / AAIF)

Agent discovery and task routing. AACP structures the content of messages that A2A routes between agents.

Existing APIs and JSON

Internal service-to-service communication. AACP complements structured systems by providing a shared coordination vocabulary for the LLM agent layer on top.

08 · Integrations

Framework integrations

Drop-in adapters replace LLM-driven coordination calls with deterministic AACP packets. Measured against a full department-day workflow (59 coordination calls).

LangChain
59 coordination calls → 0
18% total saving
CrewAI
59 coordination calls → 0
30% total saving

Positioning

AACP is not a runtime, orchestration platform, or model framework.

It is a lightweight coordination protocol and encoder framework designed to make agent workflows more structured, deterministic, and observable.

09 · Blog

Latest from the blog

All posts →