Stop Waiting for the Digest

One of the clearest public examples comes from the St. Gallen Endowment's work tracking the 2026 Iran crisis. The subject is not trade or investment. It is a geopolitical crisis. But the operating model is directly relevant, and the team has documented it in unusual detail.

Their monitor does not wait for headlines. Three times a day it runs a structured collection process before doing any analysis at all. A single cycle fires off roughly thirty-eight searches and scans somewhere between two and four hundred results, but reads only a dozen or so pages in full and admits just twenty-five to thirty verified developments into its intelligence file. Scaled up, the funnel is stark.

That is the part worth paying attention to. The value is not in collecting more information. Everyone can collect more information. The value is in rejecting more of it, consistently and according to rules. Duplicates are removed. Undated material is downgraded or excluded. Old developments are treated as context, not news. Claims that matter have to be checked against the original source rather than a search snippet. And the system watches its own source mix, capping any single outlet at forty percent of citations and requiring at least one non-Western source every cycle, so it does not end up repeating one media ecosystem's view of the world.

It even logs where searches return nothing. That sounds like a small thing, but it matters. In a watched domain, silence can be useful. A quiet week in a market, a sector, or a competitor jurisdiction tells you something, and so does the moment that silence breaks.

The system also keeps a layer of its search surface deliberately adaptive. Eight subject domains are queried every cycle, but a separate scanner reviews each day what was collected against what might have been missed, then writes new targeted queries to close the gaps. New lines of inquiry are added and retired as the situation evolves, so the monitor reshapes itself around the problem instead of waiting for a human to reconfigure it.

None of this is magic. It is just good analytical hygiene, made systematic. These are the habits we try to teach junior officers: check the source, check the date, read the original, separate what is new from what is merely repeated, and ask what is missing. The trouble is that busy teams skip those steps, not because they are careless, but because the day gets away from them. A well-designed system does not get tired or bored, and it never decides that this week is too busy to check the original.

The interesting part is not the dashboard itself. It is the judgment that sits underneath it. What should the system watch, which sources count, how recent something must be before it is treated as a development, what is noise, and what would actually change a decision. That is where the professional expertise sits.

The St. Gallen team is blunt about where the value lives: in their own phrase, the governance layer matters more than the model. The person who designs the system is the one encoding professional judgment into its rules. Their monitor runs fourteen separate analytical agents, each grounded in a different theoretical framework, each assessing the same evidence in isolation so they cannot herd toward an easy consensus, with a red team whose standing job is to argue the strongest case against whatever everyone else concluded. A trade or investment monitor almost certainly does not need fourteen competing analysts. But the principle is exactly portable: a system is only as good as the judgment encoded into what it watches, what it trusts, and what it is forced to challenge.

This is also where a lot of off-the-shelf monitoring falls short. If you work in investment attraction, you know which competitor jurisdictions are genuinely relevant and which only look similar from a distance, which sectors your region has a real case to make in, and which company announcements are meaningful rather than corporate theatre. If you work in trade promotion, you know which regulatory changes could affect exporters, which importers actually matter, which tenders are worth watching, and which market signals usually precede a commercial opening.

That knowledge is the system design. The point is not to let a machine decide what matters. It is to encode enough of your judgment that the machine can help you look in the right places, with more consistency than a human team can manage on its own. A monitoring service gives you someone else's view of relevance. A system you build reflects yours.

The problem with most intelligence products is not that they contain bad information. It is that they do not force much thought. A digest can be useful, but it is easy to skim and forget, and it gives the feeling of being informed without necessarily changing the work.

A useful dashboard should be more demanding. It should tell you what changed, why it might matter, what is still uncertain, and what deserves a closer look. For an investment team, that might mean tracking rival jurisdictions: incentive changes, major project wins, site-readiness announcements, infrastructure decisions, ministerial travel, and sector-specific policy moves. Not because any one item is decisive, but because the pattern may show where competition is heading. For a trade team, it might mean watching a target market for regulatory notices, buyer expansion, procurement signals, logistics disruptions, commodity movements, and corporate language that points to future demand. For a mission team, it might mean keeping a country brief alive between the planning meeting and the wheels-up date, since too many mission briefs are accurate when drafted and stale by the time they are used. And for a small regional office, it might simply mean watching the few sectors where the region has a credible offer and ignoring almost everything else.

That last point matters. The purpose is not comprehensive coverage. The purpose is useful coverage.

There is an obvious objection here, especially in government: our IT people will never allow this. Sometimes that is true. Often it depends on what you are trying to build, because there are really two different use cases, and they should not be treated as one.

The first is an external dashboard built only on public information. No confidential company information, no internal briefing notes, no personal data, no cabinet material, no client records. This is where most teams should start. Public information does not mean there are no rules; you still need to use tools your organization permits and avoid putting sensitive material where it does not belong. But the risk profile is much lower than anything involving internal files.

The second use case is internal. That version may be more valuable, but it belongs inside approved infrastructure, with security, privacy, records-management, and data-classification rules built in from the start. It is not a weekend experiment.

None of this makes the dashboard an intelligence product on its own. A pile of scraped links is not analysis, and a chatbot summary is not judgment. A polished interface can still be wrong, out of date, or biased. The discipline matters more than the tool.

The St. Gallen team is candid on this point. They describe their own monitor as better than headlines but well short of intelligence: a machine layer that extends human reach, is honest about its limits, and is meant to sharpen expert judgment rather than replace it. That instinct is the one to copy. The system needs dated, sourced, verifiable inputs and a diverse mix of sources. It has to separate a new development from an old fact being repeated, show disagreement rather than smooth it away, and report what it did not find as well as what it did.

And it still needs a human who understands the file. A machine can gather, filter, compare, and challenge. It can help a small team see more of the field and make weak signals easier to notice. It cannot tell you whether a minister should take the meeting, whether an investor is serious or just testing incentives, or what the politics behind a local workforce issue really are. It cannot read the relationship history behind a company visit, or the significance of what was not said in a meeting. It can sharpen the question. You still have to answer it.

For years, better intelligence mostly belonged to the organizations with bigger budgets, bigger teams, and better subscriptions. That advantage is eroding. A small office can now build a public monitoring system that would have required a dedicated analyst or an external provider not long ago. A regional team can track competitor jurisdictions; a trade office can watch several markets with more discipline than a generic digest provides; an investment team can pick up early corporate signals before they become formal announcements. The advantage is shifting from who can buy the feed to who can design the system.

That is good news for small teams willing to learn. It is less comfortable for teams still waiting for someone else to summarize the market.

The first version does not need to be ambitious. Pick one question your team actually cares about. Which jurisdictions are beating us in our target sectors? Which companies are showing early signs of expansion? Which regulatory changes could affect our exporters? Which infrastructure, permitting, energy, or workforce signals should we be watching before they turn into investment announcements? Then build around that question.

Do not start with the tool; start with the judgment. What would matter, what would not, what should be checked, what should be ignored, and what would challenge the team's current assumptions. That is the useful work.

The full build is deliberately left out here, the exact tools, the configuration, the prompts that make one of these actually run, because it is far better shown than described. A walkthrough is coming that builds a working external dashboard from scratch, start to finish, so you can watch one come together and then make your own. For now, the shift itself is the point, along with the fact that the first version, the one that could change how your team reads its market, asks nobody's permission.