ComposableStack.AI · Subject Matter Expert Series

CDP Recommendation Agent

Unbiased guidance on your Customer Data Platform architecture — Packaged vs. Composable, latency tiers, vendor tradeoffs. Every recommendation cites a knowledge-graph node so you can verify the source. The graph evolves daily through reflective evolutionary search.

Structured assessment

Four-section questionnaire — goals, technical context, organization, use cases — that maps your situation onto the knowledge-graph axes.

Grounded conversation

Agent responses cite specific KG node IDs. Click any citation to verify the underlying source — vendor doc, raw note, or web reference.

Self-improving daily

Eight scheduled routines reflect on conversations, refine the KG, and open PRs against the content + agent + UI repos.

Proposed Research Topics

Topics queued for upcoming articles. Sign in to give the researcher your priority signal. Updates daily.

View all
kg-evolutionbloglinkedin

Your Vendor Comparison Spreadsheet Is Going Stale Right Now, Whether You're Watching or Not

A first-ever systematic recency audit of a CDP knowledge base this week found that 91 of its 92 technical-side entries hadn't been re-verified against the market in 67 to 120 days — not because anyone made an error, but because re-verification has no natural trigger; nothing breaks visibly when a comparison note quietly stops matching reality. The audit's own conclusion is instructive: rather than manufacturing 91 hollow timestamp updates, it flagged which entries are foundational (most depended-upon) and prioritized those for real re-verification first. The same discipline — routine, prioritized staleness checks rather than a one-time evaluation treated as permanent — applies directly to any organization's internal CDP vendor comparison doc.

implementation-pitfallbloglinkedin

"We're Going All-In on One Vendor" Still Needs a Dependency Map

A knowledge-graph review this week had to formally document that Salesforce Data 360 is a prerequisite for Salesforce Marketing Cloud Next functioning usefully in the same stack — Marketing Cloud has no profile store of its own and can't execute sends without Data 360 upstream. Buyers who choose 'go all-in on one vendor' specifically to reduce integration risk often stop asking dependency questions once the vendor is chosen, but a single-vendor suite is still a system of internally dependent parts (the same pattern shows up in Adobe's AEP-plus-Journey-Optimizer stack and Oracle's Unity-plus-CX suite) — and if one layer lags or migrates, the layers built on top of it are blocked regardless of which company's logo is on the contract.

tradeoff-deep-divemedium

"Warehouse-Native" Is Not a Binary Claim — Ask What Still Lives Outside Your Warehouse

Tealium markets itself against an increasingly warehouse-native competitive field, and its own knowledge-graph body addition this week concedes the nuance explicitly: even with an IYOM (in-your-own-metadata) integration pattern, Tealium still maintains its own proprietary profile store as the activation-layer system of record — IYOM narrows the footprint but doesn't eliminate it. The angle generalizes past Tealium: 'warehouse-native' is a spectrum vendors self-report on, and evaluators who need a genuinely zero-proprietary-store architecture should verify the specific claim against the specific implementation rather than accepting the category label.

org-structureblog

Before You Scope an Automotive CDP, Answer Who Owns the Customer: the Dealer or the OEM

Automotive is emerging as a distinct CDP vertical in 2026 (CDK Global's built-in dealership CDP launch at NADA 2026 among the signals), but the technology story — unifying DMS records, connected-vehicle telemetry, and service history — sits on top of an organizational fault line that determines almost everything else: in a franchise/dealer-network structure, is the dealer or the OEM the party with governance authority over the unified profile? That answer changes the CDP's buyer, its data-sharing agreements, and its architecture before a single vendor gets evaluated.

Latest Knowledge-Graph Updates

Nodes and daily proposals from the last 14 days. Sign in to flag any as helpful, incorrect, or needing more depth. Updates daily.

View all
node updatesource

HIPAA Privacy Rule — Updated for 2026 (HIPAA Journal)

source.hipaajournal-com.hipaa-privacy-rule-2026

HIPAA Journal comprehensive overview of the HIPAA Privacy Rule, updated for 2026, covering PHI definition, permitted uses and disclosures, marketing restrictions, and written authorization requirements.

node updatearchetype

Salesforce Ecosystem Enterprise Evaluating CDP

archetype.salesforce-ecosystem-enterprise-evaluating-cdp

An enterprise with Salesforce CRM and Salesforce Data 360 as the incumbent CDP layer, now evaluating whether Data 360's segmentation and Marketing Cloud Next's Agentforce orchestration are sufficient for their use cases, or whether composable augmentation (Hightouch or Fivetran Activations over an existing CDW) adds meaningful value — particularly for CDW-native ML models, cross-cloud data, or segment volumes that require warehouse-native computation.

node updaterecommendation

Salesforce Ecosystem CDP Evaluator — Deepen into Data 360 or Augment with Composable Activation

recommendation.salesforce-ecosystem-cdp-deepen-or-composable-augment

For an enterprise with Salesforce CRM and Salesforce Data 360 (incumbent or planned) as the CDP layer, the evaluation is not "Salesforce vs. composable" but "where does the canonical customer profile live and which activation paths need to be served?" Path 1 (Deepen) commits to Data 360 + Marketing Cloud Next + Agentforce as the unified stack. Path 2 (Augment) keeps Data 360 as the Salesforce-ecosystem profile layer while adding a CDW-native composable activation layer (Hightouch or Fivetran Activations) for CDW-held ML models and non-Marketing-Cloud channels. The choice is driven by CDW data access requirements, ML model location, and channel breadth — not by cost alone.

How this is different

Most CDP guidance is packaged with a vendor recommendation attached. This agent is built on a knowledge graph that enforces bias-neutrality in its routine: every Vendor mention must link to at least one alternative-to edge. The recommendation isn't "use X" — it's "given your profile, here are the directions worth considering, here's the tradeoff, here's how you'd verify."

Read how it works →