Independent, public-source analysis
Find the idea
behind the update.
Search by question, narrow the collection by theme and reading time, or switch views to scan the ideas that matter to your work.
Parallelize the Work, Not the Uncertainty
Key concept: Parallelize independent work, then verify before synthesis.
Use Examples Effectively
Examples are one of the most reliable ways to steer Claude's format, tone, and structure. Instead of only describing what a good answer should look like, demonstrate the pattern you want Claude to reproduce. A useful mental model: Instruction → tells Claude the rule.
Risk-Weighted Autonomy
Risk-weighted autonomy: give agents more freedom for routine, reversible, bounded actions and require stronger human review when actions are external, destructive, financial, legally meaningful, production-facing, or difficult to reverse.
Add Context
Add context to improve performance. Claude can follow an instruction more intelligently when it understands the reason or motivation behind it. Context helps the model infer priorities and generalize beyond the exact wording of the instruction.
Put Policy in the Path
Key concept: Move sensitivedata governance from written guidance into an enforced checkpoint on the data path before information reaches the AI model.
When to Use Subagents
Key concept: Use subagents when context isolation, parallel execution, or a fresh perspective creates a real advantage.
Trustworthy Self-Service Analytics
Key concept: Reliable analytics agents need one governed path to the answer—not unrestricted access to every table and historical query.
Less Context, Better Context
Progressive disclosure: keep a small, stable set of principles in permanent context, then load specialist instructions only when the current task requires them.
Bounded Risk for Agentic AI
Key concept: The goal of AI governance is not zero risk. It is to make agentic risk visible, bounded, and manageable.
Agent View
Parallel agents increase throughput, but they also create cognitive load. Without a shared control surface, users must remember which sessions are working, blocked, waiting for input, or ready for review. Agent View turns that scattered activity into one visible queue.
Secure the AI-Native SDLC
AI-native security is lifecycle design. When agents write, review, test, and coordinate work, controls must be embedded in instructions, identities, permissions, CI, monitoring, and risk-based human review.
Zero Trust for AI Agents
Key concept: Give every agent only the identity, permissions, memory, and tools required for its current task.
Fix the Loop, Not the Output
Fix the process loop that creates repeated errors instead of manually repairing each individual output.
When to Use Multi-Agent Systems
Key concept: Use multiple agents only when one agent has a clear limitation.
Professional-Grade AI
Working at the frontier: How Thomson Reuters builds AI for highstakes professional work.
Workflow Orchestration Before Automation
Before automating a workflow, map how information moves across systems, where reconciliation happens, what output is required, and where human approval must remain.
Agent Workflow Patterns
Pick the agent workflow pattern before you build the agent.
GTM Workflow Automation
Start workflow automation from one painful repeated task, then package the solution as a reusable team workflow.
MCP Connectors and Enterprise Authorization
Enterprise AI access should be centrally governed, not individually improvised.
Skills as Reusable Workflows
Design AI skills as reusable workflow assets, not as long one-off prompts.
Self-Service Analytics with Claude
Self-service analytics with AI is not mainly a SQL-generation problem. It is a governance, context, metric-definition, retrieval, and verification problem.
Building Effective Human-Agent Teams
Key concept: Human-agent teams need explicit team design: public context, defined roles, a north star, verification, and gradual trust-building.
Claude Cowork Product Guide
Key concept: Move from conversational AI to delegated knowledge work.
Steering Claude Code
Put each Claude Code instruction in the control surface where it naturally belongs. The practical decision is not “how do I phrase this prompt?” It is: should this be always-on context, a scoped rule, a repeatable skill, an isolated subagent task, or a deterministic hook/permission?
Be Clear and Direct
Be clear and direct. Claude performs better when the prompt makes the desired result obvious. A strong prompt names the goal, adds the minimum context Claude needs, defines constraints, and specifies the output format.