Question 1

What is MACAW?

Accepted Answer

MACAW is the trust layer for AI agents. It provides security infrastructure that lets you control what AI agents can do, who they can do it for, and creates cryptographic proof of every action.

MACAW works by wrapping your existing AI code (OpenAI, Anthropic, LangChain, MCP) with policy enforcement. You define what's allowed, MACAW enforces it - at every boundary your AI crosses.

Question 2

What does MACAW stand for?

Accepted Answer

MACAW started as "Model Authorization and Cryptographic Agent Workflows" - can we track what the model is, what it's allowed to do, and back it with cryptographic evidence?

Then we realized it's not just LLMs. Agentic AI means we need to do this for all apps - autonomous workflows crossing multiple tools, data sources, and services.

Our big realization: instead of creating specialized behavioral solutions (prompt injection detection, hidden file access detection, etc.) which haven't worked, we

Question 3

What problem does MACAW solve?

Accepted Answer

Traditional security has fundamentally failed for agentic AI because LLMs have no syntactic boundary between instructions and data - they can't tell the difference between "summarize this email" and "ignore previous instructions." Pattern-matching defenses (prompt injection detectors, content filters) don't work because:

- LLMs are non-deterministic - same input can produce different outputs
- Attacks are semantic, not syntactic - can't detect meaning with regex
- The attack surface is unbounde

Question 4

What are the 4 boundaries AI agents cross?

Accepted Answer

Through formal analysis, we identified exactly four attack surfaces where AI agents are vulnerable - no more, no less:

| Surface | What It Is | Attack Example |
|---------|------------|----------------|
| S1: Prompts | Instructions that tell AI what to do | Prompt injection, jailbreaks |
| S2: Tools | External systems AI invokes | Malicious tool responses, confused deputy |
| S3: Data | Information AI accesses | Poisoned training data, data exfiltration |
| S4: Context | State AI accumulates |

Question 5

What is "intent + integrity"?

Accepted Answer

MACAW's security model enforces two properties at every boundary crossing. Both are necessary; neither is sufficient alone.

Intent (by-policy enforcement): Does this operation satisfy organizational policies?
- Does the user have permission for this action?
- Does policy allow this tool/model/data access?
- Are the parameters within allowed constraints?

Integrity (by-design elimination): Is this operation cryptographically authentic?
- Is the request signed by a legitimate source?
- Has the re

Question 6

Is MACAW open source?

Accepted Answer

Yes and no - different components have different licensing:

| Component | Status | Notes |
|-----------|--------|-------|
| Adapters | Open source (Apache 2.0) | SecureOpenAI, SecureAnthropic, SecureMCP, LangChain. Contributions welcome. |
| Client SDK | Free binary | Distributed via Console download. Common to all tiers. |
| Control Plane | SaaS / Hybrid | Closed source. We made it SaaS because there's a ton of operational details to get right. |
| MAPL Spec | Open | Policy language specificat

Question 7

Who is MACAW designed for?

Accepted Answer

Anyone using LLMs who cares about safety and controls should look at MACAW.

For developers building AI applications: Drop-in adapters that add security without changing your code architecture.

For enterprises in highly regulated industries (finance, healthcare, legal): Restrictive mode, crypto-at-rest, configurable signing, HSM/KMS support. MACAW is the most configurable platform out there - from founders who've worked with the most secure installations worldwide.

For teams scaling from proto

Question 8

How long does integration take?

Accepted Answer

Minutes. If you're using standard-compliant OpenAI, Anthropic, or MCP (e.g., FastMCP), it's literally lift and shift with one line of code change.

python
 Before
from openai import OpenAI
client = OpenAI()

After (one import change)
from macaw_adapters.openai import SecureOpenAI
client = SecureOpenAI(app_name="my-app")

That's it. Same API, now with policy enforcement, cryptographic signing, and full audit trail.

Question 9

Is MACAW a proxy or a wrapper?

Accepted Answer

Neither. MACAW is a distributed trust mesh.

Not a proxy (single chokepoint problems):
- Proxy = all traffic through one point = maintenance headache, scaling issues, single point of failure
- MACAW = distributed Policy Enforcement Points (PEPs) at every boundary

Distributed trust mesh benefits:
- Any node going down won't affect others and can recover
- Real-time enforcement at the edge
- Works on edge devices out of the box
- No bottleneck, linear scaling

Question 10

Why use MACAW instead of building security in-house?

Accepted Answer

Consider the cost:

Time: 6-8 weeks of custom development per application for JWT validation, policy engine, audit logging, enforcement, error handling. And that's just v1.

Skill: Do you have security engineers who understand cryptographic signing, policy algebra, distributed enforcement, and AI-specific attack vectors?

Risk: Can you afford to get it wrong? A security gap in your AI system isn't a bug - it's a breach waiting to happen.

Focus: Where do you want your engineers spending their ti

Question 11

Is MACAW a replacement for Okta/Auth0?

Accepted Answer

No - MACAW extends your identity provider, not replaces it.

Think of it as different layers:

| Layer | What It Solves | Examples |
|-------|----------------|----------|
| Identity (Okta/Auth0) | Who is this person? | Authentication, SSO, directory |
| Agentic Access Control (MACAW) | What can their AI do? | Policy enforcement, workflow governance, crypto audit |

Okta tells you Alice is authenticated. MACAW tells you Alice's AI agent can only use GPT-3.5, access public documents, and make 100

Question 12

What frameworks does MACAW support?

Accepted Answer

Primary adapters (maintained, production-ready):
- OpenAI - SecureOpenAI drop-in replacement
- Anthropic/Claude - SecureAnthropic drop-in replacement
- MCP (Model Context Protocol) - SecureMCP for tool servers
- LangChain - SecureLangChain wrapper

Others available on demand - contact us. We prioritize based on customer needs.