Disciplines → 3 of 6

Tooling & Context Engineering

Approved tools, governed integrations and context managed as code, so AI works with the organisation's standards and inside its boundaries.

Overview

Tooling & Context Engineering decides which AI tools may be used, how they connect to the organisation's systems, and what they are told. It covers tool selection and the approved catalogue, integration through open protocols, agents as non-human identities, and the prompts, skills and context packs that shape every AI output.

Two things determine the quality and safety of AI-assisted work besides the reviewer: the tool and the context it receives. Both are usually unmanaged at first, chosen by individuals and pasted in by hand. This discipline brings them under the controls that already govern software, access and documentation, so a tool can be defended to an auditor and a prompt can be traced like any other change.

What changes in existing practice

PracticeTodayWith Tooling & Context Engineering
ProcurementLicence, price and security questionnaireAdds data residency, retention, training use of inputs, audit logs and a documented exit plan
Software asset managementInventory of installed software and licencesApproved AI tool catalogue with tiers of permitted use; integrations and agents registered as assets
Identity & accessPeople and service accounts, periodic recertificationAgents and tool integrations are non-human identities with an owner, least privilege and short-lived credentials
Repository conventionsCode, tests and pipeline definitionsPrompts, skills and context packs live beside the code they serve, with owners and review rules
Docs-as-codeDocumentation written for peopleArchitecture decisions, standards and glossaries curated as context products that people and AI both consume

Key practices

Select tools against criteria a regulator would accept

Assess every AI tool before use on data residency, retention periods, whether inputs or outputs are used for training, enterprise administration, audit logs that can be exported, and integration with the organisation's identity provider and access control. Require portability: prompts, context and configuration in open formats, and a documented exit plan stating how the tool would be replaced. A tool without an exit plan is a lock-in decision, taken by default. See Governed openness.

Publish an approved tool catalogue

Keep one catalogue of approved tools, each with the highest risk tier of work it may support and the data classifications it may receive. A general-purpose assistant might be approved for low-tier drafting only; a coding assistant with enterprise controls for medium- and high-tier work under review; nothing for critical work beyond analysis. The catalogue is a guardrail: requests outside it go through selection, not around it.

Integrate through a governed allow-list

Connect tools and agents to repositories, trackers and data sources through open protocols such as the Model Context Protocol (MCP), routed through an allow-list or gateway rather than ad hoc connections from individual machines. Each integration is registered with an owner, the systems it reaches, the actions it may take and the tier it serves. The gateway logs every call, which gives the audit trail and the kill switch in one place.

Treat agents and integrations as non-human identities

Every agent, automation and tool integration gets its own identity: never a person's credentials, never a shared account. It holds the least privilege its task needs, uses short-lived credentials issued at run time, has a named human owner and is recertified on the same cycle as privileged human access. When the agent or integration is retired, its identity is revoked and its secrets destroyed. These identities belong in the element register.

Manage context as code

Prompts, skills and context packs are versioned in repositories, changed by pull request, reviewed and owned. When one changes, its evals run in the pipeline, because a one-line prompt change can alter every output that depends on it. Provenance records which version of which context produced an AI-assisted change. See Context is an asset.

Keep context clean and curate shared context products

Data classification decides what may enter a prompt or context pack: no secrets, credentials or personal data, and nothing above the classification the tool is approved for. Secret scanning and classification checks run before commit and at the gateway. Beyond hygiene, curate shared context products (architecture decisions, coding standards, domain glossaries, approved patterns) with owners and review dates, so AI output reflects how the organisation actually builds rather than generic defaults.

Controls by risk tier

TierPrevent (Guardrails)Prove (Audit Trail)Detect (Self-Monitoring)
LowCatalogue tools only; secret and classification checks on contextTool and context version recorded in provenanceUsage outside the catalogue; stale context assets
MediumIntegrations via the allow-list only; context changes reviewed by their owner; evals run on changeContext repository history links each change to its review and eval resultEval regressions after context changes; gateway calls outside declared scope
HighTools approved for high tier and the data classification involved; read-only integrations unless a specialist approves write access; short-lived credentials onlyGateway logs retained with the evidence bundle; non-human identities recertified with evidenceAlerts on privilege use, credential age and unusual integration activity
CriticalNo agent or integration holds write access to critical systems; AI tools may analyse copies onlyDocumented rationale for any AI tool used; second-line sign-off on context and accessAny attempt by an agent to reach a critical system triggers an incident

Maturity path

  1. Ad hoc — individuals choose their own tools and paste context by hand; integrations run on personal tokens.
  2. Experimenting — a shortlist of sanctioned tools; shared prompts circulate in wikis and chat without owners.
  3. Managed — approved catalogue with tiers of use; context assets in repositories with owners; agents have their own identities.
  4. Governed — integrations only through the allow-list or gateway; evals and context hygiene enforced in the pipeline; non-human identities recertified.
  5. Optimised — context managed as a product with measured effect on output quality; tools swapped using the exit plan without disruption.

Assess your organisation →

Measures

Anti-patterns

Regulatory anchors

ISO/IEC 42001 expects documented information on the AI management system (clause 7.5) and operational control over AI use (clause 8); the tool catalogue, the integration register and versioned context repositories provide both. The EU AI Act's AI literacy duty (Art. 4) applies to staff using these tools: the catalogue's tiers of permitted use and data rules are part of what they need to know.