Guidance: Analysis & Steering

In short

Guidance is a second opinion on your project. It works from what is confirmed in the project context: goals, scope, dates, budget, risks, action items, responsibilities. Out of that it builds short cards that tell you what stands out, why it matters, and what you could do about it.

Guidance does not replace your judgement. It makes sure you decide against an ordered picture of the project instead of a gut feeling. You open Guidance from the sidebar of the project.

Important: The four tabs Context, Strategic, Execution, and Coverage render only in AI+ mode. In User mode that tab bar does not exist. See the section on the two modes below.

When you need Guidance

Typical moments from a working week:

• Monday morning, and you want to know where this week's risk sits.
• Before a client meeting or a steering committee, when you need three defensible statements instead of twenty impressions.
• After a week away, with a lot of mail that arrived while you were gone.
• When the project feels restless and you cannot name the reason.
• Before you release the next phase and need to know whether the planned work covers the goals at all.

A bad moment is day one of an empty project. Without content there is nothing to analyze.

Opening Guidance

1. Open your project.
2. Click Guidance in the sidebar.
3. The heading Guidance appears top left, with a small field next to it reading AI+ or User. That field is the mode switch.
4. When it reads AI+, the four tabs Context, Strategic, Execution, and Coverage appear on the right.

The sidebar entry Guidance may carry a small number. It counts the open suggestions waiting for you.

The card view turns the state of the project into a short list of what deserves attention now.

What Guidance requires

Guidance is not an oracle. It reads your project context. If the context is thin, the findings are thin, and the app tells you so instead of guessing.

The context analysis unlocks the rest

The four tabs build on each other. Context is the only tab you can run at any time. Its result gets a quality rating, and that rating unlocks the others.

Tab	Requirement	What the app does otherwise
Context	none	always available
Strategic	context analysis rated Decent or better	Analyze strategy stays greyed out
Execution	at least two action items and a rating of Needs improvement or better	Refresh plan stays greyed out
Coverage	at least one action item	Analyze coverage stays greyed out

The possible ratings are Excellent, Good, Decent, Needs improvement, and Poor. They appear as a small badge next to the title Context Analysis.

When a button is greyed out

A greyed-out button is almost never a fault. It is a quality threshold. Hover over it and the tooltip names the reason.

How to move forward:

1. Switch to Context and click Analyze context.
2. Work through the cards that appear. Usually a goal, the scope, success criteria, a timeframe, a budget, milestones, or risks are missing.
3. Fill the gaps in the Context area of the project.
4. Run Analyze context again. As the rating rises, the other tabs open up.

Every card names an Observation, an Impact, and a Suggestion. Those three words appear in capitals in the app.

The four tabs in detail

All four tabs share the same layout. A box at the top carries the title of the analysis, the quality badge, the time of the last run (Last: …), and the start button. The content follows underneath.

Context: is the project picture complete?

This tab checks three things: completeness, correctness, and consistency. The cards below carry the headings Completeness, Correctness, Consistency, and Other Issues.

What each card tells you:

• Observation: the plain finding, for example "13 action items are overdue".
• Impact: why it matters, for example "Schedule slip threatens delivery and project credibility".
• Suggestion: the next step, for example "Review deadlines and set realistic dates".

How to read it: start with Correctness and Consistency. Contradictions are more dangerous than gaps because they produce quiet wrong decisions. Gaps under Completeness can stay open as long as you know they are open.

What follows: fill or correct the named field in the Context area. Some cards propose an action item directly. Those carry a Create, Update, or Remove button. Anything you do not need, you dismiss with the small cross. The Active and All toggles at the top right bring dismissed cards back.

Strategic: does the direction lead to the goal?

This tab does not ask whether you are busy. It asks whether the activity pays into the goal. It rates the alignment of the project and proposes course corrections.

What the cards tell you: a strategic assessment in the header, and below it suggestions that usually touch whole work packages or decisions rather than single steps.

How to read it: take the two or three cards with the largest consequence. The rest is material for later. Guidance only knows what is in the project. Contractual detail, politics inside the client team, or a verbal promise are included only if you recorded them.

What follows: discuss the card with your team, decide, and record the decision in the Trail area under Decisions. A strategic insight nobody writes down is gone in four weeks.

This is what the threshold looks like in practice. Only a sufficiently good context analysis opens the tab.

Execution: what is due now?

This tab is about work in motion. The box at the top shows a line such as "14 action items tracked, 6 high priority" and a recommendation below it. The button reads Refresh plan.

Two sub-tabs sit underneath.

Sub-tab Critical Path

Shows the action items in recommended order, with an eye on dependencies and on what can run in parallel. Cards carry labels such as Step 3, Can parallelize, and Critical Path.

How to read it: this is your scheduling logic. Whatever sits near the front will push the end date if it slips. Without a previous analysis the area stays empty and offers you Analyze.

What follows: make sure the leading steps have an owner and a realistic date.

Sub-tab Action Items

Shows the currently most important action items as cards. Each card carries its number, the status (Open, In Progress, Blocked), the priority with an AI+ or user badge, the complexity, the due date, and the tracked time.

You act directly on the card:

• Set In Progress moves the status to In Progress.
• Complete moves it to Completed.
• Block asks for a reason and marks the item Blocked.
• Start Timer and Track Time book working time.
• The small icon at the top right detaches the card into its own window, which you can keep on top.

Above the cards on the right you control the display: people selection, Group By, Filter & Sort, and Show Completed.

This is the same data as in the Actions area. What you complete here is complete everywhere.

The cards are not a copy of your action item list. They are an extract: what counts now.

Coverage: does the work pay into the goals?

This tab compares goals and success criteria with the planned work. The button reads Analyze coverage.

The view has two panels, and you can drag the divider between them:

• Goal Coverage: one entry per goal with the state No coverage, Partial, Adequate, or Over-invested, plus Contributing Items, Gaps, and Recommendations.
• Success Criteria Analysis: rates whether your success criteria are measurable (Quantitative, Qualitative, Vague) and which goals have no measurable criterion at all. Proposed criteria can be adopted with Add to Success Criteria.

How to read it: No coverage does not necessarily mean the work is missing. It may be named confusingly, filed under the wrong package, or not linked at all. Over-invested is the opposite case and at least as valuable: a lot of effort aimed at a goal nobody prioritizes any more.

What follows: either you create the missing work, or you correct the assignment, or you drop a goal that no longer applies. All three are valid answers.

AI+ and User: the two modes

The small switch next to the Guidance heading has two states. They are labelled AI+ and User in the interface, identically in both languages. One click flips it. The app remembers your choice per project. New projects start in AI+.

What AI+ shows

The full view: the four tabs, the AI analyses, the cards with Observation, Impact, and Suggestion, the critical path, and the coverage panels. Every analysis is an AI call. On the TensorPM provider it consumes credits.

What User shows

Considerably less, by design. In User mode the entire tab bar disappears. What remains is a single list: your action items, sorted by rules you define yourself. There is no context analysis here, no strategy, no critical path, and no coverage.

A gear icon appears next to the heading with the tooltip Configure custom priority. It opens the Configure Custom Priority window:

• Max Items to Show limits the list.
• Priority Presets offers Focus on Deadlines, Quick Wins, and Highest Impact.
• Under Prioritize By you build your own rules from Priority, Urgency, Due Date, Complexity, Impact, and Status, each with a direction such as Highest to Lowest or Oldest to Newest.
• Add Criterion adds another rule, and the arrows change their order. The top rule wins; the next one breaks ties.
• Save Priority applies everything.

So User mode is not a second view of the same analyses. It is a manual weighting of your work without any AI evaluation.

Priorities: AI+ versus User on a single action item

Regardless of the mode, every action item carries two priority values. On the card and in the action item list a small badge next to the number shows which one currently applies:

Badge	Origin	Editable
AI+	calculated by the AI, with a rationale in the tooltip	no, while AI+ is displayed
user	set by you	yes

Clicking the badge switches between them. As soon as you change the number by hand, your value applies.

In practice: the AI raises "Get fire safety certificate approved" to 100 because several items depend on it and the date is approaching. But you know from a phone call this morning that the authority will not answer for four weeks. So you switch to user and set 40. The card moves back and the list reflects reality again. If you never set your own value, TensorPM keeps working with the AI+ value.

Which mode when

• Use AI+ when you are steering: start of the week, steering meeting, phase gate, after an absence.
• Use User when you only want to work through a calm, self-sorted list.
• Use User as well when you deliberately do not want to spend credits this week.

How Guidance connects to the rest of the project

Guidance has no data of its own. It reads and writes exactly what the other views show.

Action items

The cards in the Execution tab are real action items from the Actions area. Status, priority, and time tracking are the same values. When you accept a suggestion from Context or Strategic, it becomes a new action item or a change to an existing one.

Work packages

Every action item belongs to a category. When the work breakdown structure (WBS) is active, that category is either a structure node or a work package. Every recommendation you accept therefore lands in the right place in your structure instead of floating free. Details in Work Packages & Work Breakdown Structure.

Risks

If the project has no risks or no mitigations, the Context tab reports it with the observation "No risks documented". Conversely, recorded risks feed into the strategic assessment. You maintain them in the Context area under Risks.

Trail

Guidance makes no decisions and records none. What you decide because of a card, you record in the Trail area under Decisions. Every change to the project appears there under Changes together with its origin.

What Guidance is not

Four things you might expect that Guidance deliberately does not do:

1. Not an automation. No analysis changes your project by itself. Every card needs your click.
2. Not a decision. The card names observation, impact, and suggestion. Whether the suggestion makes sense for your building project is your call.
3. Not a guarantee. The analysis uses a language model on the state of your project. It can miss something or overweight something. Check the evidence before you act.
4. Not a substitute for knowledge that exists nowhere. What lives only in your head cannot be taken into account. That is exactly why maintaining the project context is not busywork.

The responsibility stays with you. Guidance makes sure you carry it with a better view.

A practical example: an office building on Königstraße

An existing office building is being refurbished and extended by one storey. Heritage protection is involved, asbestos was found, and the client sits in the Friday meeting. The site manager steers the project in TensorPM.

Monday: taking stock

She opens Guidance. The mode is AI+, all four tabs are there, but Strategic and Coverage are greyed out. The tooltip says: run a context analysis first.

She clicks Context and then Analyze context. Shortly afterwards the badge Needs improvement appears next to Context Analysis. Two cards show up:

• Under Correctness: "13 action items are overdue", impact "Schedule slip threatens delivery and project credibility", suggestion "Review deadlines and set realistic dates".
• Under Consistency: "No recurring action items for a long-running project".

Tuesday: straightening the context

She walks through the 13 overdue items. Four were finished long ago and simply never ticked off. Five get new, realistic dates. Four stay overdue because they really are stuck, among them the question of who bears the asbestos costs.

In the Context area she adds two missing success criteria and records the asbestos issue under Risks with a mitigation. Then she runs Analyze context again. The rating climbs to Decent, which unlocks Strategic and Coverage.

Wednesday: strategy

She switches to Strategic and clicks Analyze strategy. The assessment says, in essence, that the schedule holds as long as the permits keep moving, but that the unresolved cost question can block the new storey.

She takes two cards seriously and leaves the rest. The first proposes preparing a decision paper for the client. She clicks Create. The suggestion becomes the action item "Prepare decision paper on asbestos cost responsibility", filed under the work package "Hazardous material removal".

Thursday: execution

On Execution she clicks Refresh plan. The header reports "14 action items tracked, 6 high priority".

In the Critical Path sub-tab the fire safety certificate for the timber storey sits at the front, followed by the variation order for the sandstone portal. Both have an owner, both have a date. Good.

In the Action Items sub-tab the card "Get fire safety certificate approved" catches her eye: priority 100 with the AI+ badge. From the phone call she knows the authority will not respond before the end of the month. She switches the badge to user, sets 40, and clicks Block on another card with the reason "Waiting for authority approval".

Friday: coverage before the client meeting

Before the meeting she opens Coverage and clicks Analyze coverage. Under Goal Coverage the goal "Usable office space by Q1" sits at Adequate. The goal "Heritage-compliant facade" sits at Partial, with the gap "no action item for sign-off of the sample bay".

Under Success Criteria Analysis one criterion is flagged as Vague. The proposed replacement is measurable. She clicks Add to Success Criteria.

In the meeting she presents three points: the open cost question with the decision paper, the gap around the sample bay, and the schedule-critical fire safety certificate. Afterwards she records the decision in the Trail area under Decisions.

What is different at the end of the week

The AI did not save the project. The site manager decided. But she decided against a checked picture, she found the gap around the sample bay before the client did, and the reasoning is written down in the project.

A routine for the steering meeting

1. The day before, update blocked and overdue action items.
2. Run Analyze context and clear the cards under Correctness and Consistency.
3. Run Analyze strategy and note the two or three most important cards.
4. In the Critical Path sub-tab, check that the leading steps have an owner and a date.
5. Before a phase gate, also run Analyze coverage.
6. In the meeting: present observation, impact, and suggestion. Do not read the analysis aloud.
7. After the meeting: turn agreed interventions into action items with an owner and a date.
8. Record decisions in the Trail area under Decisions.

Frequently asked questions

Why do I see no tabs? The mode is set to User. Click the field next to the Guidance heading until it reads AI+.

Do I have to run all four analyses every time? No. Context is worth running regularly because it unlocks the others. Strategic and Coverage matter mostly before decisions. Refresh Execution when the set of action items has changed noticeably.

Does every analysis cost credits? Every analysis is an AI call. Through the TensorPM provider it consumes credits. With your own provider key (Business only), billing runs through your provider. Details in Account, Subscriptions & AI Modes.

How old is the result I am looking at? The header of each tab shows Last: …. Hover over it for the exact date. Guidance does not recalculate on its own.

Can I get rid of a card that does not fit? Yes, with the small cross on the card. The All toggle at the top right brings it back. Do not keep everything open: a list that contains everything says nothing.

Does Guidance change anything without me? No. The analysis produces suggestions. Only Create, Update, or Remove changes data.

Why does a recommendation differ from my own judgement? Because Guidance only knows what is in the project. If your knowledge comes from a phone call, record it. Then the next analysis will take it into account.

What does Over-invested mean in goal coverage? That an unusual amount of planned work pays into a single goal. That can be correct. More often it is a sign that another goal is being neglected.

If something does not work

Symptom	Cause	Fix
The tab bar is missing	User mode is active	Switch to AI+
Analyze strategy greyed out	context rating below Decent, or no analysis yet	Run Analyze context, close the gaps, analyze again
Refresh plan greyed out	fewer than two action items, or the context rating is too low	Create action items, improve the context
Analyze coverage greyed out	the project has no action item at all	Create at least one action item
The list stays empty in User mode	no custom priority saved	Open Configure Custom Priority from the gear icon and save
Empty list although action items exist	filters or the people selection are too narrow	Reset Filter & Sort, clear the people selection
An error instead of a result	AI provider unreachable, credits exhausted, or the request was cancelled	Check the connection and your balance, then run it again. See Troubleshooting
The result looks outdated	analyses do not run automatically	Start the analysis again in the relevant tab
Suggestions keep repeating	the underlying gap is still open	Fix the cause in the Context area instead of dismissing the card

Next steps

• Improve the foundation: Project Structure & Context
• Turn recommendations into work: Actions & Recurring Work
• Structure and progress: Work Packages & Work Breakdown Structure
• Ask follow-up questions: Project Agent, Chat & Quick Actions
• Review decisions and changes: Files, Incoming Signals & Trail
• Where the analyses also appear: Navigation & Views