Every Cognilium AI engineering writeup grouped by subject area. Each hub starts with a foundational guide and continues into the supporting writeups.
What legal operations lose inside an ERP, and what AI can actually read, check and propose against the signed agreement. Contract review against your own playbook, obligation extraction, renewal and notice dates, and third-party paper, in Dynamics 365 Business Central and Finance & Supply Chain Management.
Where Microsoft's Copilot stops and purpose-built models start — and why the Dynamics channel's advice always ends at 'use Copilot, carefully'.
Safety stock, reorder points, coverage groups and the buffer the planning engine plans TO but never recomputes.
Which platform carries which capability, what a licence actually covers, and what each release wave changes.
The mechanism every Optimizer shares: read the system of record, compute the decision, write it back behind a human approval step.
What happens between an emailed quote request and a sent Business Central quote — one queue, identity, line matching, supplier choice and review — and where Sales Order Agent stops.
Slotting, batching and routing — what each method does, the data it needs, and where it stops being worth doing.
Where Microsoft's first-party agents in Dynamics 365 — Finance, Account Reconciliation, Payables, Expense, Collections — do the routine, and where a custom build takes over: agent readiness, the governance gap, auditability, procedures codified as business skills, and the last-mile MCP Action tools that let an agent reach your customized Finance & Operations and Business Central.
Realised price versus list, discount drift, and finding the leak in posted sales lines.
What happens between a contract arriving and a lawyer seeing it — extraction, category routing, parallel scoring, and the escalation rules that decide which clauses a person must read.
What a Commerce assortment records — a channel, a product, a date range — and the allocation depth, size curve and store clustering it never derives.
When many agents beat one and when they do not: the decision gate, orchestration topologies, coordination, cost, and how to evaluate the result.
Why production knowledge graphs decay and how to keep them correct: entity resolution, mislink detection, grounding checks, scoring and audits.
RAG → GraphRAG migrations, hybrid retrieval, security, and the patterns that ship when the vector DB stops being enough.
How AI agents remember: working, episodic, semantic and procedural memory, the context-window limit, retrieval, and the knowledge graph behind it.
Eval suites, judge loops, smart routing, retry/circuit-breaker patterns, and the day-2 ops that keep a production LLM pipeline honest at scale.
AgentCore, ADK, framework comparisons, multi-agent orchestration, and the deploy/observability stack production agents actually need.
Production voice systems on Twilio + ElevenLabs + Whisper — latency, compliance, and the architecture that survives a real call volume.
Pipelines that turn unstructured PDFs into validated structured data — extraction, evidence-mapping, cross-document linking and multi-tenancy.