Onboarding new AI hires calls for context engineering – here’s your 3-step action plan

Comply with ZDNET: Add us as a preferred source on Google.

ZDNET’s key takeaways

• Profitable adoption of AI brokers requires context engineering. 
• Context engineering requires entry to knowledge, metadata, course of movement, and extra.
• Context engineering ensures your knowledge is prepared for agentic AI utilization. 

Why is it that your present workers initially outperform the brand new rockstar you have simply employed?  And why do you have got a interval of onboarding earlier than a brand new rent will get in control?

Institutional data. The brand new rockstar is aware of easy methods to do the job. That is why you employed them.  However they want time to know the corporate tradition, processes, approaches, purposes, their group, and prospects and companions. 

Additionally: Is that a scam? This new ChatGPT trick scans suspicious numbers, emails, and links – for free

Within the AI world, the institutional data is known as context.  AI brokers are the brand new rockstar workers. You’ll be able to onboard them in minutes, not months. And the extra context that you would be able to present them with, the higher they will carry out. 

Now, while you hear reviews that AI brokers carry out higher once they have correct knowledge, assume extra broadly than buyer knowledge. The information that AI must do the job successfully additionally consists of the info that describes the institutional data: context.

We’ll get to context engineering in a minute.

Understanding context

So let’s take a look at the several types of context, its supply, and whether or not it is structured or unstructured — all of which can decide how it’s introduced to the AI agent. 

Additionally: More workers are using AI than ever – they’re also trusting it less: Inside the frustration gap

You retain listening to about fashions having a big context window. Claude has a 1-million-token context window; ChatGPT 5.2 has a 400,000-token window. However this isn’t enough to deal with all the things in regards to the firm. Take into account Salesforce’s org configuration — 20 apex courses of comparatively excessive complexity are over 250,000 tokens. So, we must be selective and supply the context for the position that the AI agent is delivering: context engineering.

Context engineering

As you may see from the desk under, a lot of this info is unstructured. Your workers are good at decoding it and filling within the gaps utilizing their judgment and making use of institutional data. AI brokers can now parse unstructured knowledge, however should not pretty much as good at making use of judgment when there are conflicts, nuances, ambiguity, or omissions. For this reason we get hallucinations. 

So the context you present must be full and AI-readable. However the context additionally must be particular to the position of the AI agent, so the context window shouldn’t be overwhelmed. The best way to do that is to think about the end-to-end course of that the AI agent is performing and use that to scope the context. That requires parsing the assorted purposes that retailer the context to tug the best degree of knowledge. If we take a look at Salesforce’s acquisitions, it begins to make sense: Data360, Informatica, MuleSoft, and Tableau are all totally different types of context at scale.

Additionally: Is your AI agent up to the task? 3 ways to determine when to delegate

Context in context

As we have mentioned, offering the right context to the AI Agent on the proper degree of element means parsing these knowledge sources with a transparent understanding of what the end-to-end course of it’s attempting to carry out.  

This can be a mixture of the documented enterprise course of and the appliance configuration encoded within the metadata and dependencies. And this isn’t nearly whether or not metadata makes use of different metadata, however why and the way. 

The method maps present visibility into guide actions between purposes or inside purposes. The accuracy and completeness of the documented course of diagrams differ wildly. Entrance-office processes are typically very poor. Again-office processes in regulated industries are sometimes superb. And to take advantage of the facility of AI brokers, organizations have to streamline them and optimize their enterprise processes. This has sparked a course of reengineering revolution that mirrors the one within the Nineteen Nineties. This time round, the extent of element required by AI brokers is larger than for people.

Additionally: Gen AI boosts productivity, but only for certain developers – here’s why

The understanding of the app configuration by the metadata and dependencies is accessible, however it’s usually confused by excessive ranges of technical debt. And it requires subtle evaluation to be full and reliable. AI brokers should not but able to taking all of the metadata and making sense of it. There is just too a lot knowledge. The one method is to make use of very intelligent, agentic workflows of chained surgical duties to run the evaluation. 

Is your content material prepared for AI?

For every kind of content material, we have to ask 5 questions

1. Does the data exist, who owns it, and what incentive have they got to help the venture?
2. Is it updated, and what’s the course of for sustaining and governing it?
3. Is it written for AI, and what modifications must be made to forestall ambiguity and confusion?
4. The place ought to or not it’s saved so AI can entry it, and what safety and entry controls ought to be utilized?
5. How ought to or not it’s structured and tagged for curation, balancing particulars with token utilization?

Let’s take a look at three content material varieties — tradition, enterprise course of, and purposes — and think about every in flip.

Firm tradition

That is the data that’s sometimes supplied to new workers throughout onboarding, however additionally it is the intangible data that’s absorbed over time. AI brokers want all of it unexpectedly. 

Additionally: Forget the chief AI officer – why your business needs this ‘magician’

• Existence and possession: This refers back to the onboarding content material the group makes use of, together with firm insurance policies. AI brokers do not care how dry the content material is. It can be different paperwork that present the tradition and persona of the group — the advertising model tips, annual reviews, and shareholder displays. Even the type of buyer testimonials, advertising movies, and workplace design will present colour to a clean canvas. Perhaps there’s a desk of company acronyms. The complication is that that is owned by totally different groups. There’s work they should put in to help the venture, however what are their priorities and incentives? Ideally, advertising ought to take the lead.
• Legitimate and precious: Of all the corporate documentation, that is most likely saved moderately present, until there was a current re-brand. If that’s the case, you’ll want to watch out what to incorporate. It might be updated, however is it nonetheless related and precious?
• Written for AI: The onboarding materials could have been written for presenting to new starters, not for studying. Therefore, there may very well be enormous context gaps, which must be full of a preamble or notes. Different content material must be set in its personal context. For instance, the AI agent must be advised easy methods to interpret buyer testimonial movies or model tips. Firm coverage paperwork are sometimes written for people, with nuances and assumptions that the AI agent won’t choose up throughout onboarding and thru tribal data.
• Entry and safety: This content material is usually unstructured and excessive quantity. The shopper testimonials could must be transcribed to textual content moderately than listed as video. Which means that an answer like Information 360 must be used to make it accessible and simply searched. Nonetheless, we additionally want to think about the safety and entry controls. Is there IP,  delicate knowledge, or private info that shouldn’t be uncovered? The safety degree of two or three units of knowledge when held in isolation could also be far decrease than when they’re mixed. As soon as the info is aggregated, the safety degree could also be many ranges larger based mostly on the insights that at the moment are accessible.
• Construction and tagging: That is troublesome knowledge to construction, as just about all of it’s required as background for the AI agent moderately than within the context of delivering a course of. There’s a steadiness between offering all the data at an in depth degree and the price and feasibility of the token utilization. So you’ll want to think about easy methods to categorize the info in order that it may be sliced and diced and served as much as the AI agent in essentially the most token-efficient method.

Enterprise operations/course of

The documented enterprise processes are the crucial construction for the AI agent to ship an consequence. However in addition they describe the supporting processes that encompass the AI agent and on which it depends or delegates. 

Additionally: Stop using ChatGPT for everything: My go-to AI models for research, coding, and more (and which I avoid)

• Existence and possession: Most organizations have processes documented. In 30+ years of working in enterprise course of engineering, we have discovered that processes are usually incomplete, old-fashioned, and in a wide range of codecs. Thankfully, you don’t want to get each course of updated; solely those associated to the AI agent you’re constructing, that are possible owned by one or two enterprise items. The processes have to cowl each the automated and human actions, however at a far better degree of element. AI brokers don’t deal with nuances, gaps, and ambiguity in addition to people do. Now you need to use AI that will help you construct the primary minimize course of. It might generate course of diagrams from notes, diagrams, and even programs metadata. These will be refined by working with leaders and customers.
• Legitimate and precious: A very powerful course of to doc and optimize is the method of course of enchancment. This turns into critically necessary for AI brokers that may take content material actually, and depend on up-to-date processes documentation to behave as anticipated. 
• Written for AI: AI is superb at understanding process-related diagrams and procedural paperwork. The difficulty is the standard of the documentation: its completeness, accuracy, and forex.
• Entry and safety: Once more, if it is unstructured documentation, akin to photos, an answer like Information 360 is required to make it accessible and simply searchable. However course of diagrams may very well be introduced as structured JSON, which is extra simply consumed by AI.
• Construction and tagging: That is very particular to the scope and consequence of the AI agent. Due to this fact, the metadata of the method diagrams is necessary. 

Software configuration

The appliance metadata describes the info construction, enterprise logic, and permissions of a selected utility. If AI brokers span utility boundaries, the content material must be augmented by architectural diagrams that describe how purposes work collectively. Additionally included in these diagrams may very well be how the brokers work collectively. 

Additionally: 5 ways you can stop testing AI and start scaling it responsibly in 2026

• Existence and possession: This knowledge is saved inside each utility as metadata. Nonetheless, it must be greater than a listing of metadata. It wants to incorporate metadata dependencies, such because the metadata evaluation that Components.cloud produces for Salesforce. An utility like Informatica is designed to retailer metadata from a number of programs.
• Legitimate and precious: The metadata is 100% correct. The metadata evaluation will be carried out each time it modifications, so it can be 100% correct.
• Written for AI: Metadata is very structured, and due to this fact, ideally suited to being learn by AI.
• Entry and safety: As it’s extremely structured, it may be saved in any database. What’s crucial is how it’s structured in order that it may be accessed. The difficulty is that any utility has far an excessive amount of metadata, and it’ll overwhelm the token limits.
• Construction and tagging: The metadata must be associated again to the operational enterprise processes that the AI agent is delivering and the info sources that the AI agent wants.

Solely 7% of communication is phrases 

There’s the widespread expression that communication is simply 7% phrases. So what in regards to the different 93%?

• The phrases (7%): Verbal content material (the literal which means).
• The tone (38%): Voice high quality, pitch, and quantity.
• The visuals (55%): Facial expressions and physique language.

Tonality acts because the punctuation of spoken language. Let’s take the easy sentence: “I wish to see you in my workplace.” Context is the 93%. We instruct AI with phrases; the 7%. Is it any surprise we get hallucinations and inconsistent outcomes? We have to present the opposite 93%. The context. This might embrace: the connection between the shopper and firm, the relative significance of various facets of the info, the stage within the course of, the urgency, and the worth of the end result. And that context is supplied as phrases and knowledge. So we have to guarantee that there may be context for the context.

Additionally: The best AI chatbots of 2026: I tested ChatGPT, Copilot, and others to find the top tools now

Context engineering is a brand new time period for AI brokers, however the content material already exists inside organizations as institutional data that folks take up over time. AI brokers are constructed to simply accept a firehose of knowledge however require it to be correct and unambiguous. That has implications for organizations that wish to faucet into the advantages of AI brokers able to delivering subtle outcomes. Here’s a 3-step motion plan:

1. Doc the scope of your AI brokers, together with the end-to-end course of and outcomes.
2. Establish the crucial contextual info required for AI brokers to carry out on the highest ranges, and assessment their high quality.
3. Format the contextual info within the platforms that may curate it for AI brokers.

This text was co-authored by Ian Gotts, senior analysis fellow at Keenan Vision, co-founder of Components.Cloud, 10X creator, tech advisor, speaker, and investor.