63 articles
You have two pieces of a working agent — an instruction from Part 1, a context file from Part 3. The third piece is the example, and the trick is you don't write it. Run the agent without one. Fix the instruction or the context — not the output — until what comes back is what you'd send. That output is your example.
On April 17, Anthropic launched Claude Design — free on every paid Claude plan, turning prompts and source data into branded slides, PDFs, and reports. For CAS practices, three patterns are worth your time this quarter — and one principle decides whether the tool actually pays off.
Sage and PwC's Beyond the Black Box research put a number on AI's hidden cost: finance professionals spend 12.9 hours a week reconstructing and explaining AI outputs, with 26% of AI time savings lost to verification. The 71% rejection rate the headlines led with is the future cost; the 12.9 hours is what your firm pays now — usually out of partner time. The fix is to stop shipping AI deliverables alone and start shipping them with a research memo and a cross-model verification report.
Intuit attached a public price tag to AI-driven close work at $8 per client per month, Sage rebuilt its portfolio around agents at Sage Future, and the standalone tools you pay for every month shipped AI rebuilds the same week. The bookkeeping service line is being absorbed into the platform subscription in front of you. The 71% trust gap from Sage's IDC research is the only thing slowing it down — and trust is a lagging constraint, not a permanent one.
For months I've been writing about client context like its meaning is obvious. It isn't. This is the article where we stop talking about context engineering in the abstract and actually build one — a single document that makes every agent you run for a client better, and that lets you take the same agent to every other client just by swapping files.
Thomson Reuters' 2026 report says 74% of tax clients want their firms using AI. Two-thirds have no idea if their firm is doing it. The fix is making the AI work you're already doing visible — one sentence at the start of your next client meeting.
For six weeks, the AI tool most CAS firms now run on was producing degraded output, and the vendor didn't know until customers complained. Three tests every CAS firm should build this month — drift detection, portability evaluation, and version trail accountability — to know when your AI vendor breaks something quietly.
KPMG cut 7% of its US audit partners. OpenAI reclaimed the model frontier with GPT-5.5 the same week Anthropic published a quality post-mortem on Claude Cowork, and Salesforce, OpenAI, Microsoft, and Google all shipped agent-first infrastructure in five days. The pattern beneath the news: partner equity, vendor strategy, and per-seat pricing are no longer safe harbors.
Your first agent shouldn't live inside your accounting platform. Start where the door is already open.
Accenture just cut 11,000 and trained 70,000 in AI — what CEO Julie Sweet called "exiting people where reskilling isn't viable." McKinsey's data says only 14% of firms have leaders like that. If your practice's AI investment isn't producing results, the bottleneck isn't your tools or your team. It's you.
Most CAS practices are using AI to solve a cost problem. PwC's April research shows that's the 80% position — and it caps your upside. Here's what the 20% are doing instead, and why your niche is the prerequisite for getting there.
PwC and Accenture both restructured around AI this week. Anthropic shipped Opus 4.7 and quietly moved enterprise billing to per-token pricing. OpenAI bought its way into personal finance. Here's what a week like this means if you're running a CAS practice.
