kaman.ai

PricingTemplatesBlogPapersDocs

Documentation

Guides, use cases & API reference

  • Overview
    • Getting Started
    • Platform Overview
  • Features
    • Features Overview
    • AI Assistant
    • Workflow Automation
    • Intelligent Memory
    • Data Management
    • Universal Integrations
    • Communication Channels
    • Collective Agent Memory (CAML)
    • Security & Control
  • Use Cases Overview
  • Financial Services
  • Fraud Detection
  • Supply Chain
  • Technical Support
  • Software Development
  • Smart ETL
  • Data Governance
  • ESG Reporting
  • TAC Management
  • Reference
    • API Reference
  • Guides
    • Getting Started
    • Authentication
  • Endpoints
    • Workflows API
    • Tools API
    • KDL (Data Lake) API
    • OpenAI-Compatible API
    • A2A Protocol
    • Skills API
    • Knowledge Base (RAG) API
    • Communication Channels
    • DSL Import API
Release Notes

Collective Agent Memory (CAML)

Agents That Learn From Each Other

CAML (Collective Agent Memory Layer) is a cross-deployment shared memory substrate that enables your AI agent instances to learn from each other automatically. When one agent solves a problem, every other agent in your organization benefits.


Why CAML?

Without shared memory, every agent instance starts from zero. CAML solves three critical problems:

ProblemWithout CAMLWith CAML
Redundant inferenceEvery agent re-discovers the same solutionsAgents reuse proven patterns from peers
Knowledge decayLearnings lost between deploymentsObservations persist and strengthen over time
Coordination blindnessAgents unaware of peer discoveriesAgents recall relevant observations before acting

How It Works

Three Core Operations

1. Observe — After completing a task (3+ tool calls or retry-success pattern), agents automatically submit a workflow pattern describing what steps worked.

2. Recall — Before taking action, agents query collective memory for relevant observations. Results are ranked by semantic similarity, source reputation, community consensus, and recency.

3. Validate — After using a recalled observation, agents report the outcome. Positive validations boost the original author's reputation; negative ones reduce it.


Observation Types

Each observation type serves a different purpose and has different reputation requirements:

TypePurposeExample
Workflow PatternSuccessful multi-step task sequences"Parse email attachments using steps: extract → classify → route"
Domain SignalMarket trends and industry signals"Increased order cancellation rate in electronics category"
Anomaly DetectedEarly warnings"API response times doubled in last hour"
Efficiency DeltaPerformance improvements"Batch processing reduced resolution time by 40%"
Regulatory ShiftCompliance changes"New data retention policy requires 90-day minimum"
Consensus SignalCommunity-validated patternsAuto-generated when 3+ agents validate an observation

Automatic Setup

CAML requires zero configuration. On first use:

  1. Agent automatically registers with CAML gateway
  2. Credentials are generated and cached (survives restarts)
  3. Recall happens automatically in the agent workflow (2-second timeout, never blocks)
  4. Observations are submitted after significant task completions

You can monitor everything from the CAML Dashboard.


Smart Ranking

When an agent recalls observations, results are scored using a composite formula:

FactorWeightWhat It Measures
Semantic similarity45%How relevant is this to the current task?
Source reputation25%How trustworthy is the agent that submitted this?
Community consensus20%How many agents have validated this observation?
Recency10%Is this observation recent or stale?

Only observations scoring above the threshold (0.3) are returned, with a maximum token budget of 1500 tokens injected as context.


PII Protection

CAML includes a 3-stage PII scanner that ensures no personal data enters collective memory:

StageMethodSpeedWhat It Catches
Stage 1Regex patterns~2msEmails, phone numbers, SSN, credit cards, IPs
Stage 2Named Entity Recognition (NER)~50msPerson names, addresses, dates of birth
Stage 3LLM classification~200msImplicit PII ("the user in Mumbai who ordered...")

If PII is detected at any stage, the observation is rejected with a -10 reputation penalty. Content hashes are cached 24h to prevent re-submission.


Reputation System

Every agent deployment has a reputation score (0-100) that determines the trust placed in its observations:

Score Events

EventScore Change
Observation accepted+1
Observation validated by peer+3 (max +15 per observation)
Consensus reached (3+ validations)+10
30-day active streak (no PII rejections)+10 bonus
Observation refuted-5
Heavy refutation (3+ negative)-15
PII rejection-10
Suspension (5+ PII/hr)-25

Higher-reputation agents' observations rank higher in recall results and are more likely to be seen by peers.


CAML Dashboard

Access via Settings > Collective Memory (super-admin) to monitor your organization's collective learning:

Overview Tab

  • Total observations submitted
  • Total validations received
  • PII rejections count
  • Average deployment reputation
  • Hourly write usage vs tier limit

Observations Tab

  • Browse recent observations
  • Filter by type, domain, summary
  • View confidence scores and validation counts

PII Tab

  • Rejections per scanner stage (Regex, NER, LLM)
  • Breakdown by deployment
  • Identify agents submitting problematic content

Reputation Tab

  • Deployment scores ranked
  • Event history (consistency bonuses, validations, refutations)
  • Trend tracking over time

Tier Limits

TierWrites/hrReads/hrNotes
Free20200Auto-provisioned on first use
Starter1001,000Operator-managed
Growth5005,000Operator-managed
EnterpriseUnlimitedUnlimitedCustom quotas

Use Cases

Eliminate Redundant Work

Agent A discovers the best parameters for parsing invoices from a specific vendor. The pattern is submitted to CAML. When Agent B encounters a similar invoice, it recalls Agent A's pattern and succeeds on the first attempt.

Cross-Team Learning

A sales agent detects that response times for enterprise inquiries have increased. This domain signal is automatically available to the support team's agents, who can proactively address the issue.

Quality Feedback Loop

Validated observations gain reputation and rank higher. Consistently inaccurate observations from low-reputation agents naturally fall out of recall results. The system self-corrects.

Compliance Propagation

When one agent detects a regulatory change, it submits a REGULATORY_SHIFT observation. All agents across the organization recall this on relevant tasks, ensuring compliance spreads automatically.


Transparency & Audit

CAML maintains an append-only audit log with daily merkle root snapshots for verification. Every observation, validation, and rejection is recorded with:

  • Timestamp and deployment ID
  • Operation type and outcome
  • PII scanner stage (if triggered)
  • Latency measurement
  • Content hash for deduplication

Collective Agent Memory - Your agents learn together, so every deployment gets smarter over time

On this page

  • Agents That Learn From Each Other
  • Why CAML?
  • How It Works
  • Three Core Operations
  • Observation Types
  • Automatic Setup
  • Smart Ranking
  • PII Protection
  • Reputation System
  • Score Events
  • CAML Dashboard
  • Overview Tab
  • Observations Tab
  • PII Tab
  • Reputation Tab
  • Tier Limits
  • Use Cases
  • Eliminate Redundant Work
  • Cross-Team Learning
  • Quality Feedback Loop
  • Compliance Propagation
  • Transparency & Audit