garethmanning/education-agent-skills/sourcing-skill-builder

Sourcing Skill Builder

What This Skill Does

Designs targeted instruction to develop students' sourcing practice — the habit of interrogating who authored a historical document, when, why, for what audience, and what this means for the document's reliability — before and during reading. The output includes a developmental progression (what sourcing looks like from novice to proficient at the specified level), an explicit instruction sequence with a teacher think-aloud script, source-type-specific guiding questions, common failure patterns with instructional responses, and assessment indicators that distinguish between students who mention sources and students who interrogate them.

Sourcing is the foundational move in historical thinking. Wineburg and Reisman (2015) described it as the touchstone distinguishing expert from novice practice in every study of historical reading. But there is a critical distinction between routinised sourcing (students habitually glance at the source note because they have been trained to) and analytical sourcing (students use source information to generate hypotheses about the document's reliability, purpose, and relationship to other accounts before reading a word of the text). Gottlieb and Wineburg (2012) demonstrated that historians and non-historians referenced sourcing at similar frequencies — the difference was not how often they mentioned the source but what they did with the information. A scientist noted the authors' names and moved on. A historian mined the title, publisher, and date to generate hypotheses about the text's political stance, all from bibliographic information alone. This skill targets both levels — building the habit first, then deepening the analytical quality — because the first without the second produces students who perform sourcing as a classroom ritual rather than an intellectual practice.

AI is specifically valuable here because diagnosing why students fail to source requires distinguishing between several different failure modes that require different instructional responses. A student who skips the source note entirely needs different intervention than a student who reads the source note but doesn't use the information, who in turn needs different intervention than a student who uses source information but applies it superficially.

Evidence Foundation

Wineburg (1991) established sourcing as an expert-novice discriminator through a landmark study comparing how historians and high school students read historical documents. Historians consistently examined the source of a document before reading its content — checking who wrote it, when, and under what circumstances. Students dove straight into the text. This finding has been replicated and extended across multiple studies (Wineburg, 1998; Rouet et al., 1997; Leinhardt & Young, 1996; Nokes, Dole & Hacker, 2007), making sourcing the most robustly documented feature of expert historical reading.

Wineburg (2007) explained why sourcing is cognitively "unnatural" through the mechanisms of spread of activation and the availability heuristic. When a document mentions a familiar topic, the reader's existing knowledge and opinions flood into the reading, overwhelming attention to the document's provenance. Disciplinary sourcing counteracts this default by training readers to pause — to resist engaging with the content until they have considered who produced it and why. Wineburg called the expert disposition that follows from this pause the "specification of ignorance": using a document not to confirm what one already believes but to articulate what one does not yet know.

Gottlieb and Wineburg (2012) refined the picture by showing that the quantity of sourcing references was similar between historians and PhD scientists/engineers — both groups noticed and mentioned source information. The difference was qualitative. A historian confronted with a book by unknown authors published by Free Press mined every word of the bibliographic information to generate hypotheses about the text's topic, political orientation, and relationship to contemporary debates. Scientists noted the same information and moved on. This finding means that teaching students to mention sources is necessary but insufficient — instruction must also develop the analytical depth of what students do with source information.

Reisman (2012) demonstrated that sourcing is teachable through explicit instruction in urban high school classrooms. In a six-month quasi-experimental intervention, treatment students showed significant gains in sourcing (F(1,181) = 15.89, p < .001, ηp² = .08). Sourcing was one of only two historical thinking skills (alongside close reading) that showed significant treatment effects — contextualisation and corroboration did not respond to the same instructional approach. Reisman attributed this to sourcing's concreteness: it involves a discrete, observable action (looking at the source note before reading) that can be modelled, practised on a single document, and reinforced until it becomes habitual.

Wineburg and Reisman (2015) characterised sourcing as not merely a strategy but a weltanschauung — a worldview that reconfigures the relationship between reader and text. When sourcing becomes habitual, the textbook's implicit claim to unassailable factual authority is disrupted. Reading becomes a dialectic between an active agent and a human author whose motives, limitations, and circumstances must be considered.

Input Schema

The teacher must provide:

• Historical topic: The topic, period, or question students are investigating. e.g. "The causes of the American Revolution" / "Life in the trenches during World War I" / "The impact of the transatlantic slave trade on West African societies" / "Did Pocahontas rescue John Smith?"
• Student level: Age/year group and current experience with primary sources. e.g. "Year 7, first time working with primary sources" / "Year 10, have done some document analysis but don't source consistently" / "Year 12 IB History, can source when prompted but don't do it independently"
• Current challenge: What students currently do or fail to do. e.g. "They dive straight into reading the text without looking at the source information" / "They note the author but don't think about what the author's position means for the document's reliability" / "They dismiss sources as 'biased' without explaining how the bias shapes the content" / "They treat all primary sources as equally trustworthy because they're 'from the time'"

Optional (injected by context engine if available):

• Source type: The type of historical source — affects what sourcing questions are most productive
• Available documents: The specific documents students will work with
• Curriculum framework: DIG, Seixas Big Six, national curriculum, IB, etc.
• Prior instruction: What sourcing instruction students have already received

Prompt

You are an expert in historical thinking pedagogy, with deep knowledge of Wineburg's (1991, 1998, 2007) research on sourcing as a disciplinary reading practice, Gottlieb and Wineburg's (2012) finding that the quality of sourcing — not the quantity — distinguishes expert from novice readers, and Reisman's (2012) evidence that sourcing is teachable through explicit instruction. You understand that sourcing is the foundational move in historical thinking: interrogating who authored a document, when, why, for what audience, and what this means for its reliability — before engaging with the document's content.
 
Your task is to design targeted sourcing instruction for:
 
**Historical topic:** {{historical_topic}}
**Student level:** {{student_level}}
**Current challenge:** {{current_challenge}}
 
The following optional context may or may not be provided. Use whatever is available; ignore any fields marked "not provided."
 
**Source type:** {{source_type}} — if not provided, design for written primary sources as the default, noting how the approach would differ for visual or non-textual sources.
**Available documents:** {{available_documents}} — if provided, tailor the instruction to these specific documents. If not, design generalisable instruction with placeholder examples.
**Curriculum framework:** {{curriculum_framework}} — if provided, align the sourcing questions and progression descriptors to this framework. If not, use the DIG framework (who wrote this, what is their perspective, why was it written, when, where, is it reliable) as the default.
**Prior instruction:** {{prior_instruction}} — if provided, build on what students have already learned rather than repeating it. If not, assume this is early-stage sourcing instruction.
 
Design the following:
 
1. **Sourcing progression:** What sourcing looks like at three levels for this age group:
   - **Novice:** The student engages with the document's content without attending to its source. Describe what this typically looks like with this age group and topic — the specific things students say, write, or do that reveal they are not sourcing.
   - **Developing:** The student notes source information but uses it superficially. Describe what "superficial sourcing" looks like — e.g. mentioning the author but not considering their position, noting the date but not reasoning about what was happening at that time, labelling a source as "biased" without explaining how the bias shapes the content.
   - **Proficient:** The student uses source information to generate hypotheses about the document's reliability, purpose, and perspective before and during reading. Describe what this looks like with this topic — the specific questions a proficient student would ask, the inferences they would draw from the bibliographic information, the way source awareness shapes their reading of the content.
 
   IMPORTANT: The distinction between developing and proficient is the distinction Gottlieb and Wineburg (2012) identified — the difference between mentioning a source and interrogating it. Make this distinction concrete and observable for this specific context.
 
2. **Explicit instruction sequence:** A three-part sequence for moving students from their current challenge toward proficient sourcing:
   - **I DO (teacher models):** A think-aloud script (approximately 150–200 words) showing the teacher encountering the document's source information and modelling what an expert reader does with it. The think-aloud should make visible the internal reasoning that is normally invisible — pausing at the source note, generating questions from the author's name and position, forming hypotheses from the date and publication context, noting what is NOT in the source information and why that matters. The think-aloud must be specific to the source type and topic, not generic.
   - **WE DO (guided practice):** A structured activity where students practise sourcing a second document with teacher support. Specify what the teacher does (circulates, prompts, redirects), what questions the teacher asks when students skip the source or use it superficially, and how the teacher gradually withdraws support.
   - **YOU DO (independent practice):** What independent sourcing looks like — students source a third document without prompting. Specify what the teacher monitors for and how to assess whether students are sourcing habitually or only when reminded.
 
3. **Guiding questions:** Source-type-specific questions for students, calibrated to the developmental level. These should be adapted from the DIG sourcing protocol but made specific to the source type. For each question, include:
   - The question itself
   - Why this question matters for this source type (brief, one sentence)
   - A sentence starter students can use when responding